Merge pull request 'https' (#13) from https into master

Reviewed-on: #13

.gitignore

@@ -0,0 +1,4 @@
+backup*/
+wp-navigation
+*.log
+__pycache__/

backup_canalblog.sh

@@ -3,8 +3,8 @@
 TAR=/usr/bin/tar
 PYTHON=/usr/bin/python3
 GZIP=/usr/bin/gzip
-SCRIPTDIR=/home/valentin/script
-WEBSCRAP=${SCRIPTDIR}/web_scrap.py
+SCRIPTDIR=/home/valentin/script/webscrap
+WEBSCRAP=${SCRIPTDIR}/import_export_canalblog.py
 URL=www.clarissariviere.com
 DATE=$(date +%Y%m%d)
 DIRECTORY=/home/valentin/backup
@@ -24,8 +24,8 @@ else
 fi
 subject="${subject} ${URL} ${DATE}"
 echo > ${BACKUPDIR}/${LOGFILE}
-${PYTHON} ${WEBSCRAP} --url ${URL} --dir ${DIRECTORY}  --quiet --logfile ${BACKUPDIR}/${LOGFILE}
-if [ ${?} -ne 0 ]; then
+${PYTHON} ${WEBSCRAP} --quiet --logfile ${BACKUPDIR}/${LOGFILE} --parallel 20 export --url ${URL} --directory ${DIRECTORY}  
+if [ ${?} -ne 0 ]; then 
 	subject="${subject} echoue : recuperation page"
 	echo ${subject} | mail -s "${subject}" -A ${BACKUPDIR}/${LOGFILE} ${SENDER}
 	exit 1

import_export_canalblog.py

@@ -0,0 +1,284 @@
+#!/usr/bin/python3
+from requests.auth import HTTPBasicAuth
+from getpass import getpass
+from urllib.parse import urlparse
+from concurrent import futures
+from concurrent.futures import as_completed, wait
+
+import argparse, logging, threading
+from lib.WPImport import WPimport
+from lib.WPExport import WPExport
+from lib.WPRemove import WPRemove
+
+def remove(args, basic, logger, ssl_wordpress):
+    removeWp = WPRemove(basic=basic, wordpress="", logger=logger, ssl_wordpress=ssl_wordpress)
+    if args.remove == True:
+        for i in args.wordpress.split(","):
+            removeWp.setUrl(i)
+            removeWp.cleanPosts()
+            removeWp.cleanTags()
+            removeWp.cleanCategories()
+            removeWp.cleanMedia()
+    else:
+        for i in args.wordpress.split(","):
+            removeWp.setUrl(i)
+            if args.posts == True:
+                removeWp.cleanPosts()
+            if args.categories == True:
+                removeWp.cleanCategories()
+            if args.tags == True:
+                removeWp.cleanTags()
+            if args.media == True:
+                removeWp.cleanMedia()
+    del removeWp
+
+
+def download(name_thread, max_thread, url, logger, parser, directory, html, img, ssl_canalblog):
+    exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, directory=directory, ssl_canalblog=ssl_canalblog)    
+    webpage = exportWp.getUrlPage(name_thread, max_thread)
+    for i in ["article", "page"]:
+        for j in ["publications", "principal"]:
+            if html is False:
+                exportWp.downloadHTML(webpage[j][i])
+
+            if img is False:
+                exportWp.downloadImg(webpage[j][i])
+
+
+
+
+def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, basic, serial, ssl_wordpress, ssl_canalblog):
+    canalblog = canalblog.split(",")
+    wordpress = wordpress.split(",")
+    name = "Thread-{0}".format(int(name_thread) + 1)
+    protocol = "https"
+    if ssl_canalblog is False:
+        protocol = "http"
+    if serial is False:
+        for canal in canalblog:
+            try:
+                o = urlparse(canal)
+                o = o._replace(scheme=protocol)
+                url = o.geturl().replace(":///", "://")
+            except Exception as err:
+                logger.error("{0} : parsing error : {1}".format(name, err))
+                exit(1)
+            exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, ssl_canalblog=ssl_canalblog)
+            webpage = exportWp.getUrlPage(name_thread, max_thread)
+            del exportWp
+            for j in wordpress:
+                importWp = WPimport(name=name, basic=basic, wordpress=j, logger=logger, parser=parser, ssl_wordpress=ssl_wordpress)
+                for k in ["article", "page"]:
+                    for l in ["publications", "principal"]:
+                        importWp.fromUrl(webpage[l][k])
+
+                del importWp
+    else:
+        if len(canalblog) != len(wordpress):
+            logger.error("{0} : ERREUR : Le nombre de dossier n'est pas equivalent au nombre d'URL wordpress".format(name))
+            exit(1)
+        for i in range(0, len(canalblog)-1):
+            try:
+                o = urlparse(canalblog[i])
+                o = o._replace(scheme=protocol)
+                url = o.geturl().replace(":///", "://")
+            except Exception as err:
+                logger.error("parsing error : {0}".format(err))
+                exit(1)
+            exportWp = WPExport(name=name, url=url, logger=logger, parser=parser, ssl_canalblog=ssl_canalblog)
+            webpage = exportWp.getUrlPage(name_thread, max_thread)
+            del exportWp
+            importWp = WPimport(name=name, basic=basic, wordpress=wordpress[i], logger=logger, parser=parser, ssl_wordpress=ssl_wordpress)
+
+            for k in ["article", "page"]:
+                for l in ["publications", "principal"]:
+                    importWp.fromUrl(webpage[l][k])
+
+            del importWp
+    
+
+def importDirectory(name_thread, max_thread, directory, logger, parser, wordpress, basic, serial, ssl_wordpress):
+    name = "Thread-{0}".format(int(name_thread) + 1)
+    directory = directory.split(",")
+    wordpress = wordpress.split(",")
+    if serial is False:
+        for i in wordpress:
+            importWp = WPimport(name=name, basic=basic, wordpress=i, logger=logger, parser=parser, ssl_wordpress=ssl_wordpress)
+            for j in directory:
+                importWp.fromDirectory(j, name_thread, max_thread)
+                del importWp
+
+    else:
+        if len(directory) != len(wordpress):
+            logger.error("{0} : Error : Number directory is differant than wordpress".format(name))
+            exit(1)
+        for i in range(0, len(wordpress)-1):
+            importWp = WPimport(name=name, basic=basic, wordpress=wordpress[i], logger=logger, parser=parser, ssl_wordpress=ssl_wordpress)
+            importWp.fromDirectory(directory[i])
+            del importWp
+
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--debug", help="Verbosity",  action="store_true")
+    parser.add_argument("--logfile", help="Log file",  default="")
+    parser.add_argument("--quiet", help="No console output", action="store_true")
+    parser.add_argument("--parser", help="Parser content", default="html.parser")
+    parser.add_argument("--parallel", help="Define number thread (default : 1)", default=1)
+    parser.add_argument("--no-ssl", help="No ssl for canalblog and/or wordpress (example wordpress,canalblog)", dest="ssl", default="")
+
+    subparsers = parser.add_subparsers(dest="command")
+
+    import_parser = subparsers.add_parser("import")
+    import_parser.add_argument("--user", help="wordpress user", required=True)
+    import_parser.add_argument("--password", help="password wordpress's user", default="")
+    import_parser.add_argument("--file", help="HTML file", default="")
+    import_parser.add_argument("--directory", help="HTML directory", default="")
+    import_parser.add_argument("--canalblog", help="URL Canalblog", default="")
+    import_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
+    import_parser.add_argument("--serial", help="Serial execution", action="store_true")
+    import_parser.add_argument("--remove-all", dest="remove", help="Remove all", action="store_true")
+    import_parser.add_argument("--remove-posts", help="Remove all posts", dest="posts", action="store_true")
+    import_parser.add_argument("--remove-categories", help="Remove all categories", dest="categories", action="store_true")
+    import_parser.add_argument("--remove-tags", help="Remove all tags", dest="tags", action="store_true")
+    import_parser.add_argument("--remove-media", help="Remove all media", dest="media", action="store_true")
+
+
+    remove_parser = subparsers.add_parser("remove")
+    remove_parser.add_argument("--user", help="wordpress user", required=True)
+    remove_parser.add_argument("--password", help="password wordpress's user", default="")
+    remove_parser.add_argument("--wordpress", help="URL Wordpress", required=True)
+    remove_parser.add_argument("--all", dest="remove", help="Remove all (posts, media, tags, categories)", action="store_true")
+    remove_parser.add_argument("--posts", help="Remove all posts", action="store_true")
+    remove_parser.add_argument("--categories", help="Remove all categories", action="store_true")
+    remove_parser.add_argument("--tags", help="Remove all tags", action="store_true")
+    remove_parser.add_argument("--media", help="Remove all media", action="store_true")
+
+
+
+    export_parser = subparsers.add_parser("export")
+
+    export_parser.add_argument("--url", help="canblog URL to be scraping", required=True)
+    export_parser.add_argument("--directory",
+                      default="backup",
+                      help="backup file path")
+    export_parser.add_argument("--no-css", help="No CSS", dest="css",  action="store_true")
+    export_parser.add_argument("--no-js", help="No JS", dest="js",  action="store_true")
+    export_parser.add_argument("--no-img", help="No img", dest="img",  action="store_true")
+    export_parser.add_argument("--no-html", help="No HTML", dest="html", action="store_true")
+
+    
+
+    args = parser.parse_args()
+
+    logger = logging.getLogger('import export canalblog')
+    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+    ssl_canalblog = True
+    ssl_wordpress = True
+
+    for i in args.ssl.split(","):
+        if i == "canalblog":
+            ssl_canalblog = False
+        if i == "wordpress":
+            ssl_wordpress = False
+
+    if args.quiet is False:
+        ch = logging.StreamHandler()
+        if args.debug is True:
+            logger.setLevel(logging.DEBUG)
+            ch.setLevel(logging.DEBUG)
+        else:
+            logger.setLevel(logging.INFO)
+            ch.setLevel(logging.INFO)
+        ch.setFormatter(formatter)
+        logger.addHandler(ch)
+
+
+    if len(args.logfile) > 0:
+        fileHandler = logging.FileHandler(args.logfile)
+        if args.debug is True:
+            fileHandler.setLevel(logging.DEBUG)
+        else:
+            fileHandler.setLevel(logging.INFO)
+        fileHandler.setFormatter(formatter)
+        logger.addHandler(fileHandler)
+
+    if args.command == "import" or args.command == "remove":
+        password = args.password
+        if len(args.password) == 0:
+            password = getpass()
+            if len(password) == 0:
+                logger.error("No password error !!! ")
+                exit(1)
+
+        basic = HTTPBasicAuth(args.user, password)
+    if args.command == "import":
+        wordpress = args.wordpress.split(",")
+        importWp = WPimport(basic=basic, wordpress="", logger=logger, parser=args.parser, ssl_wordpress=ssl_wordpress)
+        if len(args.file) > 0:
+            for i in wordpress:
+                importWp.setUrl(i)
+                importWp.fromFile(files=args.file.split(","))
+        if len(args.directory) > 0:
+            remove(args, basic, logger, ssl_wordpress)
+            try:
+                with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
+                    wait_for = [
+                    ex.submit(importDirectory, i, int(args.parallel), args.directory, logger, args.parser, args.wordpress, basic, args.serial, ssl_wordpress)
+                    for i in range(0, int(args.parallel))
+                    ]
+            except Exception as err:
+                logger.error("Threading error : {0}".format(err))
+        if len(args.canalblog) > 0:
+            remove(args, basic, logger, ssl_wordpress)
+            try:
+                with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
+                    wait_for = [
+                    ex.submit(importUrl, i, int(args.parallel), args.canalblog, logger, args.parser, args.wordpress, basic, args.serial, ssl_wordpress, ssl_canalblog)
+                    for i in range(0, int(args.parallel))
+                    ]
+            except Exception as err:
+                logger.error("Threading error : {0}".format(err))
+        exit(0)
+
+
+    if args.command == "export":
+        canalblog = args.url.split(",")
+        protocol = "https"
+        if ssl_canalblog is False:
+            protocol = "http"
+        exportWp = WPExport(logger=logger, parser=args.parser, directory=args.directory, ssl_canalblog=ssl_canalblog)
+        for canal in canalblog:
+            try:
+                o = urlparse(canal)
+                o = o._replace(scheme=protocol)
+                url = o.geturl().replace(":///", "://")
+            except Exception as err:
+                logger.error("parsing error : {0}".format(err))
+                exit(1)
+            exportWp.setUrl(url)
+            if args.js is False:
+                exportWp.downloadJs()
+    
+            if args.css is False:
+                exportWp.downloadCss()
+            del exportWp
+
+
+    
+            if args.html is False or args.img is False:
+                try:
+                    with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
+                        wait_for = [
+                        ex.submit(download, i, int(args.parallel), url, logger, args.parser, args.directory, args.html, args.img, ssl_canalblog)
+                        for i in range(0, int(args.parallel))
+                        ]
+                except Exception as err:
+                    logger.error("Threading error : {0}".format(err))
+        exit(0)
+
+
+    if args.command == "remove":
+        remove(args, basic, logger, ssl_wordpress) 
+        exit(0)

lib/WPExport.py

@@ -0,0 +1,290 @@
+#!/usr/bin/python3
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+import requests, os, argparse, logging
+from requests.adapters import HTTPAdapter
+from requests.packages.urllib3.util.retry import Retry
+
+class WPExport:
+    def __init__(self, name = "Thread-0", url = "", logger = None, parser = "html.parser", directory = "backup", ssl_canalblog=True):
+        self._url = url
+        self._logger = logger
+        self._parser = parser
+        self._dir = directory
+        self._name = name
+        self._protocol = "https"
+        if ssl_canalblog is False:
+            self._protocol = "http"
+        
+        self._request = requests.Session()
+
+        retries = Retry(total=10,
+                status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
+
+        self._request.mount('{0}://'.format(self._protocol), HTTPAdapter(max_retries=retries))
+
+
+    # Destructor 
+    def __del__(self):
+        self._logger.info("{0} : Export finished for {1}".format(self._name, self._url))
+
+    # Public method
+
+
+    # Set name
+
+    def setName(self, name):
+        self._name = "Thread-{0}".format(int(name) + 1)
+
+    # Set URL
+
+    def setUrl(self, url):
+        self._url = url
+
+    # Download JS
+
+    def downloadJs(self):
+        script = self._getScriptCss(True, False)
+        o = urlparse(self._url)
+        self._downloadPage(script, "{0}/{1}/{2}".format(self._dir, o.path, "dists/js"))
+
+    # Download CSS
+
+    def downloadCss(self):
+        css = self._getScriptCss(False, True)
+        o = urlparse(self._url)
+        self._downloadPage(css, "{0}/{1}/{2}".format(self._dir, o.path, "dists/css"))
+
+    # Download HTML
+
+    def downloadHTML(self, webpage):
+        self._downloadPage(webpage, self._dir)
+
+    # Download Image
+    
+    def downloadImg(self, webpage):
+        page_src = self._getImg(webpage)
+        o = urlparse(self._url)
+        self._downloadPage(page_src, "{0}/{1}/{2}".format(self._dir, o.path, "img"))
+
+
+     # Get URL
+    def getUrlPage(self, index_thread, max_thread):
+        try:
+            page = self._request.get(self._url)
+        except Exception as err:
+            self._logger.error("{0} : Connection error : {1}".format(self._name, err))
+            exit(1)
+        page_url = []
+        if page.status_code == 200:
+            soup = BeautifulSoup(page.text, self._parser)
+            ul = soup.find_all("ul", id="listsmooth")
+            for anchor in ul[0].find_all("a"):
+                href = anchor.get('href', '/')
+                if href != "#":
+                    page_url.append(href)
+        else:
+            self._logger.error("{0} : URL did not get due status code : {1}".format(self._name, page.status_code))
+            self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+        webpage = {"principal": {"page":[], "article":[]}, "publications": {"page":[], "article":[]}}
+        for i in page_url:
+            section = "publications"
+            o = urlparse(i)
+            o = o._replace(scheme=self._protocol)
+            i = o.geturl().replace(":///", "://")
+            if i == "{0}/".format(self._url):
+                section = "principal"
+            try:
+                page = self._request.get(i)
+            except Exception as err:
+                self._logger.error("{0} : Connection error : {1}".format(self._name, err))
+                exit(1)
+            if page.status_code == 200:
+                self._logger.info("{0} : page : {1}".format(self._name, i))
+                if i not in webpage[section]["page"]:
+                    webpage[section]["page"].append(i)
+                soup = BeautifulSoup(page.text, self._parser)
+                class_div = soup.find_all("div", class_="pagingfirstline")
+                if len(class_div) > 0:
+                    pagingfirstline = class_div[0].find_all("a")
+                    if len(pagingfirstline) > 1:
+                        lastpage = pagingfirstline[len(pagingfirstline)-1].get("href", "/")
+                        self._logger.debug("{0} : Last page {1}".format(self._name, lastpage))
+
+                        element_lastpage = lastpage.split("/")[len(lastpage.split("/"))-1]
+                        number_page = element_lastpage.split("-")[0].split("p")[1]
+                        number_lastpage = int(number_page) / 10
+
+                        setPageDivided = int(number_lastpage) / max_thread
+                        if setPageDivided > int(setPageDivided):
+                            setPageDivided = setPageDivided + 1
+                        setPagePart = setPageDivided * (index_thread + 1)
+                        firstPagePart = (setPagePart - setPageDivided)
+
+                        self._logger.debug("{0} : Total page : {1}".format(self._name,int(number_lastpage)))
+                        self._logger.debug("{0} : First range : {1}".format(self._name, int(firstPagePart)))
+                        self._logger.debug("{0} : Last range : {1}".format(self._name, int(setPagePart)))
+
+                        for j in range(int(firstPagePart),int(setPagePart)+1):
+                            paging = j * 10
+                            categorie = urlparse(i).path.split("/")
+                            url_paging = "{0}/archives/p{1}-10.html".format(self._url, paging)
+                            if len(categorie) > 2:
+                                url_paging = "{0}/archives/{1}/p{2}-10.html".format(self._url, categorie[2], paging)
+                            self._logger.info("{0} : {1}".format(self._name, url_paging))
+                            if url_paging not in webpage[section]["page"]:
+                                webpage[section]["page"].append(url_paging)
+                            page = self._request.get(url_paging)
+                            if page.status_code == 200:
+                                soup = BeautifulSoup(page.text, self._parser)
+                                h2 = soup.find_all("h2")
+                                self._logger.debug("{0} : {1} H2 : {2}".format(self._name, url_paging, h2))
+                                for title in h2:
+                                    self._logger.debug("{0} : {1} a : {2}".format(self._name, url_paging, title.find_all("a")))
+                                    href = title.find_all("a")[0].get("href", "/")
+                                    if href not in webpage[section]["article"]:
+                                        try:
+                                            o = urlparse(href)
+                                            o = o._replace(scheme="https").geturl()
+                                        except Exception as err:
+                                            self._logger.error("parsing error : {0}".format(err))
+                                            exit(1)
+                                        webpage[section]["article"].append(o)
+            else:
+                self._logger.error("{0} : web didn't get due status code : {1}".format(self._name, page.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
+        return webpage
+        
+
+
+    # Private method
+    # 
+    # Create path        
+    def _mkdirPath(self, path_dir):
+        if not os.path.exists(path_dir):
+            makedir = []
+            pathh = path_dir.split("/")
+            for i in pathh:
+                makedir.append(i)
+                repath = "/".join(makedir)
+                if not os.path.exists(repath):
+                    self._logger.debug("{0} : Dossier crée : {1}".format(self._name, repath))
+                    try:
+                        if len(repath) > 0:
+                            os.mkdir(repath)
+                    except Exception as err:
+                        self._logger.error("Directory error : {0}".format(err))
+                        self._logger.debug("Directory error : {0} {1} {2} {3} {4}".format(err, path_dir, repath, pathh, makedir))
+                        exit(1)
+
+
+    # Get Css and JS
+    def _getScriptCss(self, js, css):
+        try:
+            page = self._request.get(self._url)
+        except Exception as err:
+            self._logger.error("Connection error : {0}".format(err))
+            exit(1)
+        page_url = []
+        if page.status_code == 200:
+            soup = BeautifulSoup(page.text, self._parser)
+            if js is True:
+                script = soup.find_all("script")
+                for anchor in script:
+                    src = anchor.get("src", "/")
+                    if src != "/":
+                        try:
+                            u = urlparse(self._url)
+                            o = urlparse(src)
+                        except Exception as err:
+                            self._logger.error("parsing error : {0}".format(err))
+                            exit(1)
+                        if o.netloc == "":
+                            o = o._replace(netloc=u.netloc)
+                            o = o._replace(scheme=u.scheme)
+                        page_url.append(o.geturl())
+            if css is True:
+                link = soup.find_all("link")
+                for anchor in link:
+                    rel = anchor.get("rel")
+                    if rel[0] == "stylesheet":
+                        href = anchor.get("href", "/")
+                        if href != "/":
+                            try:
+                                u = urlparse(self._url)
+                                o = urlparse(href)
+                            except Exception as err:
+                                self._logger.error("parsing error : {0}".format(err))
+                                exit(1)
+                            if o.netloc == "":
+                                o = o._replace(netloc=u.netloc)
+                                o = o._replace(scheme=u.scheme)
+                            page_url.append(o.geturl())        
+        else:
+            self._logger.error("JS or CSS did not get due status code : {0}".format(page.status_code))
+            self._logger.debug(page.content)
+
+        return page_url
+
+    # Get image
+
+    def _getImg(self, webpage):
+        page_img = []
+        for i in webpage:
+            try:
+                page = self._request.get(i)
+            except Exception as err:
+                self._logger.error("{0} : Connection error : {1}".format(self._name, err))
+                exit(1)
+            if page.status_code == 200:
+                soup = BeautifulSoup(page.text, self._parser)
+                img = soup.find_all("img")
+                self._logger.info("{0} : image from page: {1} : ".format(self._name,i))
+                for anchor in img:
+                    src = anchor.get("src", "/")
+                    if src != "/":
+                        if src not in page_img:
+                            self._logger.info("{0} : image: {1} : ".format(self._name, src))
+                            page_img.append(src)
+            else:
+                self._logger.error("{0} : Image did not get due status code : {1}".format(self._name, page.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+        return page_img
+
+
+    # Download page
+    def _downloadPage(self, webpage, backup_dir):
+   
+        for i in range(0, len(webpage)):
+            try:
+                o = urlparse(webpage[i])
+            except Exception as err:
+                self._logger.error("parsing error : {0}".format(err))
+                exit(1)
+            path_web = o.path.split("/")
+            filePageWeb = path_web[len(path_web)-1]
+            path_web.pop(len(path_web)-1)
+            dir_page_web = "/".join(path_web)
+            self._mkdirPath("{0}/{1}/{2}".format(backup_dir, o.netloc, dir_page_web))
+            try:
+                r = self._request.get(webpage[i])
+            except ConnectionError as err:
+                self._logger.error("{0} : Connection error : {1}".format(self._name, err))
+                exit(1)
+            except Exception as err:
+                self._logger.error("{0} Exception error : {1}".format(self._name, err))
+            if r.status_code == 200:
+                fileDownload = "{0}/{1}/index.html".format(backup_dir, o.netloc)
+                if len(dir_page_web) > 0 and len(filePageWeb) > 0:
+                    fileDownload = "{0}/{1}{2}/{3}".format(backup_dir, o.netloc, dir_page_web, filePageWeb)
+                self._logger.info("{0} : {1}/{2} : {3}".format(self._name, i+1, len(webpage), fileDownload))
+                try:
+                    open(fileDownload, "wb").write(r.content)
+                except Exception as err:
+                    self._logger.error("file error : {0}".format(err))
+                    exit(1)
+            else:
+                self._logger.error("Not download due status code : {0}".format(r.status_code))
+                self._logger.debug(r.content)

lib/WPImport.py

@@ -0,0 +1,649 @@
+#!/usr/bin/python3
+
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+import requests, os, logging, re, json
+from requests.adapters import HTTPAdapter
+from requests.packages.urllib3.util.retry import Retry
+
+class WPimport:
+    # Constructor
+    def __init__(self, name="Thread-0", basic=None, wordpress="", logger=None, parser="html.parser", ssl_wordpress=True):
+        self._name = name
+        self._basic = basic
+        self._wordpress = wordpress
+        self._logger = logger
+        self._parser = parser
+        self._headers_json = {'Content-Type': 'application/json; charset=utf-8', 'Accept':'application/json'}
+        self._protocol = "https"
+        if ssl_wordpress is False:
+            self._protocol = "http"
+        self._request = requests.Session()
+
+        retries = Retry(connect=10, read=10, redirect=5,
+                status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
+
+        self._request.mount('{0}://'.format(self._protocol), HTTPAdapter(max_retries=retries))
+
+    
+    # Destructor 
+    def __del__(self):
+        print("{0} : Import finished for {1}".format(self._name, self._wordpress))
+    
+    # Public method
+
+    def setUrl(self, wordpress):
+        self._wordpress = wordpress
+
+    def fromUrl(self, webpage):
+        for i in range(0, len(webpage)):
+            try:
+                r = self._request.get(webpage[i])
+            except Exception as err:
+                self._logger.error("{0} : Connection error for get url {1} : {2}".format(self._name, webpage[i], err))
+                exit(1)
+            if r.status_code == 200:
+                self._logger.info("{0} : ({1}/{2}) : Page is importing : {3}".format(self._name, i+1, len(webpage), webpage[i]))
+                soup = BeautifulSoup(r.content, self._parser)
+                articlebody = soup.find_all("div", class_="articlebody")
+                if len(articlebody) > 0:
+                    self._addOrUpdatePost(soup)
+                else:
+                    self._addOrUpdateFeaturedMedia(soup)
+            else:
+                self._logger.error("{0} : Connection error for get url {1} with status code : {2}".format(self._name, webpage[i], r.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, r.content))
+
+
+    def fromDirectory(self, directory="", number_thread=1, max_thread=1):
+        directory = "{0}/archives".format(directory)
+        directories = self._getDirectories([], "{0}".format(directory))
+        if len(directories) > 0:
+            files = self._getFiles(directories)
+            self.fromFile(files, number_thread, max_thread)
+        else:
+            self._logger.error("{0} : No files for {1}".format(self._name, directory))
+        
+
+    def fromFile(self, files=[], number_thread=1, max_thread=1):
+        divFiles = int(len(files) / max_thread)
+        currentRangeFiles = int(divFiles * (number_thread+1))
+        firstRange = int(currentRangeFiles - divFiles)
+        self._logger.debug("{0} : index : {1}".format(self._name,number_thread))
+
+        self._logger.debug("{0} : first range : {1}".format(self._name,firstRange))
+        self._logger.debug("{0} : last range : {1}".format(self._name,currentRangeFiles))
+
+        for i in range(firstRange, currentRangeFiles):
+            if os.path.exists(files[i]):
+                self._logger.info("{0} : ({1}/{2}) File is being processed : {3}".format(self._name, i+1, currentRangeFiles + 1, files[i]))
+                with open(files[i], 'r') as f:
+                    content = f.read()
+                    self._logger.debug("{0} : Size of article : {1}".format(self._name, len(content)))
+                    soup = BeautifulSoup(content, self._parser)
+                    articlebody = soup.find_all("div", class_="articlebody")
+                    self._logger.debug("{0} : Number of article : {1}".format(self._name, len(articlebody)))
+                    if len(articlebody) > 0:
+                        self._addOrUpdatePost(soup)
+                    else:
+                        self._addOrUpdateFeaturedMedia(soup)
+    
+    
+    # Private method
+
+    ## replace caracter 
+
+    def _replaceCaracter(self, title_rendered):
+        list_replace = {'’': "'", '–': '-', '…': '...', '« ': '"', ' »': '"', '« ': '"', ' »': '"', '’': "'", '"‘': "'"}
+        for old, new in list_replace.items():
+            title_rendered = title_rendered.replace(old, new)
+        return title_rendered
+
+    ## remove space 
+
+    def _removeSpace(self, title):
+        if title[len(title)-1] == " ":
+            title = title[:-1]
+        if title[0] == " ":
+            title = title[1:]
+        return title
+
+    ## Get all files
+
+    def _getFiles(self, item):
+        files = []
+        for i in item:
+            for j in os.listdir(i):
+                if os.path.isfile("{0}/{1}".format(i, j)):
+                    files.append("{0}/{1}".format(i, j))
+        return files
+
+    ## Get directories
+
+    def _getDirectories(self, subdirectory, item):
+        sub = subdirectory
+        for i in os.listdir(item):
+            if os.path.isdir("{0}/{1}".format(item, i)):
+                sub.append("{0}/{1}".format(item, i))
+                subdirectory = self._getDirectories(sub, "{0}/{1}".format(item, i))
+        return subdirectory
+
+    ## Add or update featured media
+
+    def _addOrUpdateFeaturedMedia(self, soup):
+        item_div = soup.find_all("div", {"data-edittype": "post"})
+        for i in item_div:
+            h2 = i.find_all("h2")[0].text
+            params = {"search":h2, "type":"post"}
+            try:
+                page = self._request.get("{1}://{0}/wp-json/wp/v2/search".format(self._wordpress, self._protocol), auth=self._basic, params=params)
+            except Exception as err:
+                self._logger.error("{0} : Connection error : {1}".format(self._name, err))
+                exit(1)
+            if page.status_code == 200:
+                result = page.json()
+                if len(result) > 0:
+                    if h2 == result[0]["title"]:
+                        img = i.find_all("img")
+                        if len(img) > 0:
+                            img_src = img[0].get("src")
+                            try:
+                                page = self._request.get(img_src)
+                            except Exception as err:
+                                self._logger.error("{0} : Connection error for get featured media : {1}".format(self._name, err))
+                                exit(1)
+                            if page.status_code == 200:
+                                name_img = img_src.replace("_q", "")
+                                name_img = name_img.split("/")[len(name_img.split("/"))-1]
+                                params = {"search": name_img}
+                                try:
+                                    page = self._request.get("{1}://{0}/wp-json/wp/v2/media".format(self._wordpress, self._protocol), auth=self._basic, params=params)
+                                except Exception as err:
+                                    self._logger.error("{0} : Connection error search featured media : {1}".format(self._name, err))
+                                    exit(1)
+                                if page.status_code == 200:
+                                    res = page.json()
+                                    if len(res) > 0:
+                                        id_media = res[0]["id"]
+                                        data = {"featured_media": id_media}
+                                        try:
+                                            r = self._request.post("{2}://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, result[0]["id"], self._protocol), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
+                                        except Exception as err:
+                                            self._logger.error("{0} : Connection error for post media featured : {1}".format(self._name, err))
+                                            exit(1)
+                                        if r.status_code == 200:
+                                            self._logger.info("{0} : Add media featured : {1}".format(self._name, r.json()["title"]["raw"]))
+                                        else:
+                                            self._logger.error("{0} : Connection error with status code for featured media : {1}".format(self._name, r.status_code))
+                                            self._logger.debug("{0} : {1}".format(self._name, r.content))
+
+                                    else:
+                                        self._logger.info("{0} : No media found for {1}".format(self._name, h2))
+                                else:
+                                    self._logger.error("{0} : Connection error with status code for search featured media: {1}".format(self._name, page.status_code))
+                                    self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+                            else:
+                                self._logger.error("{0} : Connection error for get featured media with status code : {1}".format(self._name, page.status_code))
+                                self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+            else:
+                self._logger.error("{0} : Connection error with status code for featured media : {1}".format(self._name, page.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+
+    ## Association image to post
+
+    def _linkImgPost(self, title, list_img, post_id):
+        for i in list_img:
+            data = {"post": post_id}
+            try:
+                r = self._request.post("{2}://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, i["id"], self._protocol), auth=self._basic, data=data)
+            except Exception as err:
+                self._logger.error("{0} : Connection error for link image to post : {1}".format(self._name, err))
+                exit(1)
+            if r.status_code == 200:
+                self._logger.info("{0} : Link image to post {1}".format(self._name, title))
+            else:
+                self._logger.error("{0} Connection error with status code for link image to post : {1}".format(self._name, r.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, r.content))
+
+    
+    ## Add or update img 
+
+    def _addOrUpdateMedia(self, href_img, page):
+        media_authorized = ["png", "jpg", "jpeg", "svg", "gif"]
+        media = {"id":"", "rendered":""}
+        split_fileimg = href_img.split("/")
+        img_name = split_fileimg[len(split_fileimg)-1]
+        img_type_file = img_name.split(".")[len(img_name.split("."))-1]
+        is_img = True
+        if img_type_file not in media_authorized:
+            self._logger.error("{0} : Element {1} is not image".format(self._name,img_name))
+            is_img = False
+        if is_img is True:
+            self._logger.debug("{0} : Search for image {1} with URL {2}".format(self._name, img_name, "{1}://{0}/wp-json/wp/v2/media".format(self._wordpress, self._protocol)))
+            params = { "search": img_name}
+            try:
+                r = self._request.get("{1}://{0}/wp-json/wp/v2/media".format(self._wordpress, self._protocol), auth=self._basic, params=params)
+            except Exception as err:
+                self._logger.error("{0} : Connection error for search media : {1}".format(self._name, err))
+                exit(1)
+            self._logger.debug("{0} : Search for image {1} and his status code {2}".format(self._name, img_name, r.status_code))
+            if r.status_code == 200:
+                res = r.json()
+                self._logger.debug("{0} : Number of image in search : {1}".format(self._name, len(res)))
+                if len(res) > 0:
+                    params = {"force":1}
+                    try:
+                        r = self._request.delete("{2}://{0}/wp-json/wp/v2/media/{1}".format(self._wordpress, res[0]["id"], self._protocol), auth=self._basic, params=params)
+                    except Exception as err:
+                        self._logger.error("{0} Connection error for delete image : {1}".format(self._name, err))
+                        exit(1)
+                    if r.status_code == 200:
+                        self._logger.info("{0} : Image removed {1}".format(self._name, img_name))
+                    else:
+                        self._logger.error("{0} : Image {1} not removed due status code : {2}".format(self._name, img_name, r.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, r.content))
+
+                data = page.content
+                img_type = "image/{0}".format(img_type_file)
+                if img_type_file == "jpg":
+                    img_type = "image/jpeg"
+                headers={ 'Content-Type': img_type,'Content-Disposition' : 'attachment; filename={0}'.format(img_name)}
+                try:
+                    r = self._request.post("{1}://{0}/wp-json/wp/v2/media".format(self._wordpress, self._protocol), auth=self._basic, headers=headers, data=data)
+                except Exception as err:
+                    self._logger.error("{0} : Connection error for add image : {1}".format(self._name, err))
+                    exit(1)
+                if r.status_code == 201:
+                    self._logger.info("{0} : Image added {1}".format(self._name, img_name))
+                    res = r.json()
+                    media["id"] = res["id"]
+                    media["rendered"] = res["guid"]["rendered"]
+                else:
+                    self._logger.error("{0} : Image {1}.{2} not added due status code : {3}".format(self._name, img_name, img_type, r.status_code))
+                    self._logger.debug("{0} : {1}".format(self._name, r.content))
+
+            else:
+                self._logger.error("{0} : Connection error for search image with status code : {1}".format(self._name, r.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, r.content))
+
+        return media
+
+    ## Add or update comment
+
+    def _addOrUpdateComment(self, post, comment, title):
+            for i in comment:
+
+                try:
+                    params = {"post": post, "author_name":i["author"], "date":i["date"]}
+                    page = self._request.get("{1}://{0}/wp-json/wp/v2/comments".format(self._wordpress, self._protocol), auth=self._basic, params=params)
+                except Exception as err:
+                    self._logger.error("{0} : Connection error for search comment : {1}".format(self._name, err))
+                    exit(1)
+                if page.status_code == 200:
+                    result = page.json()
+                    for j in result:
+                        try:
+                            params = {"force":1}
+                            page = self._request.delete("{2}://{0}/wp-json/wp/v2/comments/{1}".format(self._wordpress, j["id"], self._protocol), params=params, auth=self._basic)
+                        except Exception as err:
+                            self._logger.error("{0} : Connection error for delete comment : {1}".format(self._name, err))
+                            exit(1)
+                        if page.status_code == 200:
+                            self._logger.info("{0} : Comment deleted for {1}".format(self._name, title))
+                            self._logger.debug("{0} : Comment deleted : {1}".format(self._name, j))
+                        else:
+                            self._logger.error("{0} : Comment not deleted for {1} due status code : {2}".format(self._name, title, page.status_code))
+                            self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+                else:
+                    self._logger.error("{0} : Comment not listed for {1} due status code : {2}".format(self._name, title, page.status_code))
+                    self._logger.debug("{0} : {1}".format(self._name, page.content))
+   
+            for i in comment:           
+                data = {"post": post, "content": i["content"], "date": i["date"], "author_name": i["author"], "status": "approved"}
+    
+                if i["parent_id"] != -1:
+                    parent_id = int(i["parent_id"])
+                    params = {"post": post, "author_name":comment[parent_id]["author"], "date":comment[parent_id]["date"]}
+                    try:
+                        page = self._request.get("{1}://{0}/wp-json/wp/v2/comments".format(self._wordpress, self._protocol), auth=self._basic, params=params)
+                    except Exception as err:
+                        self._logger.error("{0} : Connection error for parent comment : {1}".format(self._name, err))
+                        exit(1)
+                    if page.status_code == 200:
+                        result = page.json()
+                        if len(result) > 0:
+                            data["parent"]=result[0]["id"]
+                    else:
+                        self._logger.error("{0} : Connection error for parent comment with status code : {1}".format(self._name, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+                try:
+                    page = self._request.post("{1}://{0}/wp-json/wp/v2/comments".format(self._wordpress, self._protocol), auth=self._basic, data=data)
+                except Exception as err:
+                    self._logger.error("{0} : Connection error for add comment : {1}".format(self._name, err))
+                    exit(1)
+                if page.status_code == 201:
+                    self._logger.info("{0} : Comment added for {1}".format(self._name, title))
+                    self._logger.debug("{0} : Data : {1}".format(self._name, data))
+                else:
+                    self._logger.error("{0} : Comment not added for {1} due status code : {2}".format(self._name, title, page.status_code))
+                    self._logger.debug("{0} : {1}".format(self._name, page.content))
+    
+    ## Check class name 
+
+    def _hasClassName(self, tag, className):
+        for i in tag["class"]:
+            if i == className:
+                return True
+        return False
+    
+    ## Get class name 
+
+    def _getClassName(self, tag, className):
+        for i in tag["class"]:
+            if re.match(className, i):
+                return i
+        return ""
+    
+    ## Get all comments
+
+    def _getComment(self, comment):
+        comment_post = []
+        for i in range(0, len(comment)):
+            comment_div = comment[i].find("div", class_="comment_item")
+            comment_item = comment_div.text.split("\n")
+            footer = comment_div.find_all("div", class_="itemfooter")
+            comment_author = footer[0].text.split(",")[0].replace("Posté par ", "")
+            comment_date = footer[0].find_all("abbr")[0].get("title")
+            comment_content = "<p>"
+            for j in range(0, len(comment_item)-2):
+                if len(comment_item[j]) > 0:
+                    comment_content = comment_content + comment_item[j] + "<br />"
+            comment_content = comment_content + "</p>"
+            parent = -1
+            if self._hasClassName(comment[i], "level-1") is False:
+                block = False
+                className = self._getClassName(comment[i], "level-").split("-")
+                level = 1
+                if len(className) > 0:
+                    level = int(className[1])
+                for j in range(i-1, 0, -1):
+                    if block is False:
+                        levelName = "level-{0}".format(level - 1)
+                        if self._hasClassName(comment[j], levelName) is True:
+                            parent = j
+                            block = True
+
+            comment_post.append({"author": comment_author, "date": comment_date, "content": comment_content, "parent_id":parent})
+        return comment_post
+    ## Add or Update post 
+
+    def _addOrUpdatePost(self, soup):
+        tags = []
+        month = {"janvier":"01", "février": "02", "mars": "03", "avril":"04", "mai": "05", "juin": "06", "juillet": "07", "août": "08", "septembre": "09", "octobre": "10", "novembre": "11", "décembre": "12"}
+        liste = ["categories", "tags"]
+        elements = {}
+        element = {}
+        listelement = {}
+
+        for i in liste:
+            element[i] = []
+            listelement[i] = []
+
+        articletitle = soup.find_all("h2", class_="articletitle")
+        self._logger.debug("{0} : Title of the article : {1}".format(self._name, articletitle))
+        articlebody = soup.find_all("div", class_="articlebody")
+        articledate = soup.find_all("span", class_="articledate")
+        articleacreator = soup.find_all("span", class_="articlecreator")
+        dateheader = soup.find_all("div", class_="dateheader")
+        itemfooter = soup.find_all("div", class_="itemfooter")
+        comment = soup.find_all("li", class_="comment")
+        img_a = articlebody[0].find_all("a", {"target": "_blank"})
+        self._logger.debug("{0} : Number of image's link : {1}".format(self._name, len(img_a)))
+        list_img = []
+        for i in img_a:
+            new_img = {}
+            img = i.find_all("img")
+            self._logger.debug("{0} : Number of image's tag : {1}".format(self._name, len(img)))
+            if len(img) > 0:
+                href_a = i.get("href")
+                href_img = img[0].get("src")
+                new_img["old_src"]=href_img
+                new_img["old_href"]=href_a
+                try:
+                    page_img = self._request.get(href_img)
+                except Exception as err:
+                    self._logger.error("{0} : Connection error for get image : {1}".format(self._name, err))
+                    exit(1)
+                if page_img.status_code == 404:
+                    href_img = href_a
+                    try:
+                        page_img = self._request.get(href_a)
+                    except Exception as err:
+                        self._logger.error("{0} : Connection error for get image : {1}".format(self._name, err))
+                        exit(1)
+                self._logger.debug("{0} : Status code for image {1} : {2}".format(self._name, href_img, page_img.status_code))
+                if page_img.status_code == 200:
+                    media=self._addOrUpdateMedia(href_img, page_img)
+                    new_img["id"]=media["id"]
+                    new_img["new_src"]=media["rendered"]
+                    list_img.append(new_img)
+                    if href_img != href_a:
+                        media=self._addOrUpdateMedia(href_a, page_img)
+                        new_img["id"]=media["id"]
+                        new_img["new_src"]=media["rendered"]
+                        list_img.append(new_img)
+                if page_img.status_code not in [200, 404]:
+                    self._logger.error("{0} : Connection error with status code for get image : {1}".format(self._name, page_img.status_code))
+                    self._logger.debug("{0} : {1}".format(self._name, page_img.content))
+
+        self._logger.debug("{0} : Number of image : {1}".format(self._name, len(list_img)))
+        comment_post = self._getComment(comment)
+
+        a = itemfooter[0].find_all("a", {"rel": True})
+        for i in a:
+            rel = i.get("rel")
+            if rel[0] == 'tag':
+                href = i.get("href")
+                if re.search(r'/tag/', href):
+                    element["tags"].append(i.text)
+                if re.search(r'/archives/', href):
+                    element["categories"].append(i.text)
+        for i in liste:
+            for j in element[i]:
+                element_exist = False
+                title_element = self._removeSpace(j)
+                for index in range(1,10):
+                    self._logger.info("{0} : search {1} with index {2} : {3}".format(self._name, i, index, title_element))
+                    try:
+                        params = {"search":title_element, "per_page":"100", "page":index}
+                        page = self._request.get("{2}://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i, self._protocol), auth=self._basic, params=params)
+                    except ConnectionError as err:
+                        self._logger.error("{0} : Connection error for {1} : {2}".format(self._name, i, err))
+                        exit(1)
+                    except Exception as err:
+                        self._logger.error("{0} : Exception error for {1} : {2}".format(self._name, i, err))
+                    if page.status_code == 200:
+                        result = page.json()
+                        self._logger.debug("{0} : content {3} {2} : {1}".format(self._name, result, title_element, i))
+                        if len(result) > 0:
+                            for k in result:
+                                title_rendered = k["name"]
+                                self._logger.debug("{0} : content {2} : {1}".format(self._name, title_rendered, i))
+                                self._logger.debug("{0} : size of content {3} : {2} - {1}".format(self._name, len(title_rendered), len(title_element), i))
+                                if len(title_element) != len(title_rendered):
+                                    title_rendered = self._replaceCaracter(title_rendered)
+                        
+                                if title_element == title_rendered:    
+                                    self._logger.info("{0} : {1} found : {2}".format(self._name, i, title_rendered))
+                                    element_exist = True
+                                    listelement[i].append(k["id"])
+                        else:
+                            break
+                    if page.status_code == 400:
+                        self._logger.error("{0} : {1} not found due status code : {2}".format(self._name, i, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+                        break
+                    else:
+                        self._logger.error("{0} : {1} not found due status code : {2}".format(self._name, i, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+                self._logger.debug("{0} : Element {3} {2} is {1}".format(self._name, element_exist, title_element, i))
+                if element_exist == False:
+                    data = {"name": title_element}
+                    self._logger.info("{0} : Create {1} : {2}".format(self._name, i, title_element))
+                    self._logger.debug("{0} : Data : {1}".format(self._name, data))
+                    try:
+                        page = self._request.post("{2}://{0}/wp-json/wp/v2/{1}".format(self._wordpress, i, self._protocol), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
+                    except ConnectionError as err:
+                        self._logger.error("{0} : Connection error for post {1} : {2}".format(self._name, i, err))
+                        exit(1)
+                    except Exception as err:
+                        self._logger.error("{0} : Exception error for post {1} : {2}".format(self._name, i, err))
+                    if page.status_code == 201:
+                        self._logger.info("{0} : {1} created : {2}".format(self._name, i, j))
+                        result = page.json()
+                        listelement[i].append(result["id"])
+                    else:
+                        self._logger.error("{0} : {1} not added due status code : {2}".format(self._name, i, page.status_code))
+                        self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+        title = articletitle[0].text
+        author = articleacreator[0].text.lower()        
+        body = articlebody[0].find_all("p")
+        bodyhtml = "<p>"
+        for i in body:
+            if len(i.text) == 1:
+                bodyhtml = bodyhtml + "<br />"
+            else:
+                bodyhtml = bodyhtml + str(i).replace("<p>", "").replace("</p>", "").replace("<br>", "<br />") + "<br />"
+        bodyhtml = bodyhtml + "</p>"
+        for i in list_img:
+            o = urlparse(i["new_src"])
+            bodyhtml = bodyhtml.replace(i["old_href"], o.path)
+            bodyhtml = bodyhtml.replace(i["old_src"], o.path)
+        hour = articledate[0].text
+        time = dateheader[0].text.split(" ")
+        self._logger.debug("{0} : Title post : |{1}|".format(self._name, title))
+        title = self._removeSpace(title)
+        self._logger.debug("{0} : Rendered Title post : |{1}|".format(self._name, title))
+
+        data = {"title":title, "content":bodyhtml, "status":"publish", "date": "{0}-{1}-{2}T{3}:00".format(time[2],month[time[1]],time[0], hour), "tags": listelement["tags"], "categories": listelement["categories"]}
+        self._logger.debug("{0} : Data for post : |{1}| : {2}" .format(self._name, title, data))
+
+        params = {"search":author, "per_page":100}
+        try:
+            self._logger.info("{0} : Search author : {1}".format(self._name, author))
+            page = self._request.get("{1}://{0}/wp-json/wp/v2/users".format(self._wordpress, self._protocol), auth=self._basic, headers=self._headers_json, params=params)
+            self._logger.debug("{0} : End Search author : {1}".format(self._name, author))
+            self._logger.debug("{0} : Debug requests : {1}".format(self._name, page.content))
+
+
+        except ConnectionError as err:
+            self._logger.error("{0} : Connection error for get author : {1}".format(self._name, err))
+            exit(1)
+        except Exception as err:
+            self._logger.error("{0} : Exception error for get author : {1}".format(self._name, err))
+        if page.status_code == 200:
+            self._logger.info("{0} : Get author id : {1}".format(self._name, result))
+            result = page.json()
+            for a in result:
+                data["author"] = a["id"]
+        else:
+            self._logger.error("{0} : Connection error with status code for get author : {1}".format(self._name, page.status_code))
+            self._logger.debug("{0} : {1}".format(page.content))
+        page_is_exist = False
+
+        for index in range(1,10):
+            params = {"search": title, "per_page":100, "page": index}
+            try:
+                self._logger.info("{0} : Search post with index {2} : {1}".format(self._name, title, index))
+                page = self._request.get("{1}://{0}/wp-json/wp/v2/posts".format(self._wordpress, self._protocol), auth=self._basic, params=params, headers=self._headers_json)
+            except ConnectionError as err:
+                self._logger.error("{0} : Connection error for search post : {1}".format(self._name, err))
+                exit(1)
+            except Exception as err:
+                self._logger.error("{0} : Exception error for search post : {1}".format(self._name, err))
+            if page.status_code == 200:
+                self._logger.debug("{0} : Encoding : {1}".format(self._name, page.encoding))
+                page.encoding = "utf-8"
+                result = page.json()
+                if len(result) == 0:
+                    break
+                self._logger.info("{0} : Number result posts : {1}".format(self._name, len(result)))
+                count = 0
+                for i in result:
+                    title_rendered = i["title"]["rendered"]
+                    self._logger.info("{0} : Search title posts for |{2}| : |{1}|".format(self._name, title_rendered, title))
+                    if len(title_rendered) != len(title):
+                        title_rendered = self._replaceCaracter(title_rendered)
+                    self._logger.debug("{0} : Search title posts for |{2}| : |{1}|".format(self._name, title_rendered, title))
+                    self._logger.debug("{0} : SIze of title : {1} - {2}".format(self._name, len(title), len(title_rendered)))
+                    if title_rendered == title:
+                        page_is_exist = True
+                        post_id = i["id"]
+                        count = count + 1
+                        if count > 1:
+                            self._logger.info("{0} : Page {1} is double and going to delete".format(self._name, title))
+                            try:
+                                params = {"force":1}
+                                page = self._request.delete("{2}://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id, self._protocol), auth=self._basic, headers=self._headers_json, params=params)
+                            except ConnectionError as err:
+                                self._logger.error("{0} : Connection error for deleted post : {1}".format(self._name, err))
+                                exit(1)
+                            except Exception as err:
+                                self._logger.error("{0} : Exception error for deleted post : {1}".format(self._name, err))
+                            if page.status_code == 200:
+                                self._logger.info("{0} : Post deleted : {1}".format(self._name, title))
+                            else:
+                                self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
+                                self._logger.debug("{0} : {1}".format(self._name, page.content))    
+                    
+                        else:
+                            self._logger.debug("{0} : Data for post to update : {1}".format(self._name, i))
+                            self._logger.info("{0} : Page {1} already exist and going to update".format(self._name, title))
+                
+                            try:
+                                page = self._request.post("{2}://{0}/wp-json/wp/v2/posts/{1}".format(self._wordpress, post_id, self._protocol), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
+                            except ConnectionError as err:
+                                self._logger.error("{0} : Connection error for update post : {1}".format(self._name, err))
+                                exit(1)
+                            except Exception as err:
+                                self._logger.error("{0} : Exception error for update post : {1}".format(self._name, err))
+                            if page.status_code == 200:
+                                result = page.json()
+                                self._logger.info("{0} : Post updated : {1}".format(self._name, title))
+                                self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
+                                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+                            else:
+                                self._logger.error("{0} : Post not updated due status code : {1}".format(self._name, page.status_code))
+                                self._logger.debug("{0} : {1}".format(self._name, page.content))
+            if page.status_code == 400:
+                self._logger.error("{0} : Connection for update post unauthorized : {1}".format(self._name, page.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
+                break
+            else:
+                self._logger.error("{0} : Connection for update post error with status code : {1}".format(self._name, page.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, page.content))
+
+        if page_is_exist is False:
+            try:
+                self._logger.info("{0} : Creating posts : {1}".format(self._name, data["title"]))
+                page = self._request.post("{1}://{0}/wp-json/wp/v2/posts".format(self._wordpress, self._protocol), auth=self._basic, headers=self._headers_json, data=json.dumps(data))
+            except ConnectionError as err:
+                self._logger.error("{0} : Connection error for create post : {1}".format(self._name, err))
+                exit(1)
+            except Exception as err:
+                self._logger.error("{0} : Exception error for create post : {1}".format(self._name, err))
+            if page.status_code == 201:
+                result = page.json()
+                self._logger.info("{0} : Post added : {1}".format(self._name, result["title"]["raw"]))
+                self._addOrUpdateComment(result["id"], comment_post, result["title"]["raw"])
+                self._linkImgPost(result["title"]["raw"], list_img, result["id"])
+            else:
+                self._logger.error("{0} : Post not added due status code : {1}".format(self._name, r.status_code))
+                self._logger.debug("{0} : {1}".format(self._name, r.content))

lib/WPRemove.py

@@ -0,0 +1,78 @@
+#!/usr/bin/python3
+
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+import requests, os, logging, re, json
+from requests.adapters import HTTPAdapter
+from requests.packages.urllib3.util.retry import Retry
+
+class WPRemove:
+    # Constructor
+    def __init__(self, name="Thread-0", basic=None, wordpress="", logger=None, ssl_wordpress=True):
+        self._name = name
+        self._basic = basic
+        self._wordpress = wordpress
+        self._logger = logger
+        self._headers_json = {'Content-Type': 'application/json', 'Accept':'application/json'}
+        
+        self._protocol = "https"
+        if ssl_wordpress is False:
+            self._protocol = "http"
+        self._request = requests.Session()
+
+        retries = Retry(connect=10, read=10, redirect=5,
+                status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
+
+        self._request.mount('{0}://'.format(self._protocol), HTTPAdapter(max_retries=retries))
+
+    
+    # Destructor 
+    def __del__(self):
+        print("{0} : Import finished for {1}".format(self._name, self._wordpress))
+
+    # Public method
+
+    def setUrl(self, wordpress):
+        self._wordpress = wordpress
+    
+    def cleanPosts(self):
+        self._removeAll("posts")
+
+    def cleanTags(self):
+        self._removeAll("tags")
+
+    def cleanCategories(self):
+        self._removeAll("categories")
+    
+    def cleanMedia(self):
+        self._removeAll("media")
+
+    # Private method
+    
+    def _removeAll(self, composant):
+        params = {"per_page":100}
+        try:
+            self._logger.info("{0} : List {2} to remove for url : {1}".format(self._name, self._wordpress, composant))
+            
+            r = self._request.get("{2}://{0}/wp-json/wp/v2/{1}".format(self._wordpress, composant, self._protocol), auth=self._basic, params=params, headers=self._headers_json)
+        except Exception as err:
+            self._logger.error("{0} : Connection error for list {1} to remove : {2}".format(self._name, composant, err))
+        if r.status_code == 200:
+            result = r.json()
+            if len(result) > 0:
+                for i in result:
+                    self._logger.info("{0} : Remove {2} for url {1} : {3}".format(self._name, self._wordpress, composant, i["title"]["rendered"]))
+                    params = {"force":1}
+                    try:
+                        r = self._request.delete("{3}://{0}/wp-json/wp/v2/{1}/{2}".format(self._wordpress, composant, i["id"], self._protocol), auth=self._basic, headers=self._headers_json , params=params)
+                        if r.status_code == 200:
+                            self._logger.info("{0} : Post removed for URL {1} {2} : {3}".format(self._name, self._wordpress, composant, i["title"]["rendered"]))
+                        else:
+                            self._logger.error("{0} : Connection error for post {1} {2} {3} with status code {4}".format(self._name, self._wordpress, composant, i["title"]["rendered"], r.status_code))
+                    except Exception as err:
+                        self._logger.error("{0} : Connection error for {1} remove : {2}".format(self._name, composant, err))
+                        exit(1)
+                self._removeAll(composant)
+        else:
+            self._logger.error("{0} : Error for list to remove {1} due status code {2}".format(self._name, composant, r.status_code))
+            self._logger.debug("{0} : Content error for {1} : {2}".format(self._name, composant, r.content))

web_scrap.py

@@ -1,241 +0,0 @@
-#!/usr/bin/python3
-from bs4 import BeautifulSoup
-from urllib.parse import urlparse
-import requests, os, argparse, logging
-
-def mkdirPath(path_dir, logger):
-    if not os.path.exists(path_dir):
-        makedir = []
-        pathh = path_dir.split("/")
-        for i in pathh:
-            makedir.append(i)
-            repath = "/".join(makedir)
-            if not os.path.exists(repath):
-                logger.debug("Dossier crée : {0}".format(repath))
-                try:
-                    if len(repath) > 0:
-                        os.mkdir(repath)
-                except Exception as err:
-                    logger.error("Directory error : {0}".format(err))
-                    logger.debug("Directory error : {0} {1} {2} {3} {4}".format(err, path_dir, repath, pathh, makedir))
-                    exit(1)
-
-
-def getScriptCss(url, js, css, logger):
-    try:
-        page = requests.get(url)
-    except Exception as err:
-        logger.error("Connection error : {0}".format(err))
-        exit(1)
-    page_url = []
-    if page.status_code == 200:
-        soup = BeautifulSoup(page.text, 'html.parser')
-        if js is True:
-            script = soup.find_all("script")
-            for anchor in script:
-                src = anchor.get("src", "/")
-                if src != "/":
-                    try:
-                        u = urlparse(url)
-                        o = urlparse(src)
-                    except Exception as err:
-                        logger.error("parsing error : {0}".format(err))
-                        exit(1)
-                    if o.netloc == "":
-                        o = o._replace(netloc=u.netloc)
-                        o = o._replace(scheme=u.scheme)
-                    page_url.append(o.geturl())
-        if css is True:
-            link = soup.find_all("link")
-            for anchor in link:
-                rel = anchor.get("rel")
-                if rel[0] == "stylesheet":
-                    href = anchor.get("href", "/")
-                    if href != "/":
-                        try:
-                            u = urlparse(url)
-                            o = urlparse(href)
-                        except Exception as err:
-                            logger.error("parsing error : {0}".format(err))
-                            exit(1)
-                        if o.netloc == "":
-                            o = o._replace(netloc=u.netloc)
-                            o = o._replace(scheme=u.scheme)
-                        page_url.append(o.geturl())
-                
-                
-    return page_url
-
-def getImg(webpage, logger):
-    page_img = []
-    for i in webpage:
-        try:
-            page = requests.get(i)
-        except Exception as err:
-            logger.error("Connection error : {0}".format(err))
-            exit(1)
-        if page.status_code == 200:
-            soup = BeautifulSoup(page.text, 'html.parser')
-            img = soup.find_all("img")
-            logger.info("image from page: {0} : ".format(i))
-            for anchor in img:
-                src = anchor.get("src", "/")
-                if src != "/":
-                    if src not in page_img:
-                        logger.info("image: {0} : ".format(src))
-                        page_img.append(src)
-
-
-    return page_img
-
-def getUrlPage(url, logger):
-    try:
-        page = requests.get(url)
-    except Exception as err:
-            logger.error("Connection error : {0}".format(err))
-            exit(1)
-    page_url = []
-    if page.status_code == 200:
-        soup = BeautifulSoup(page.text, 'html.parser')
-        ul = soup.find_all("ul", id="listsmooth")
-        for anchor in ul[0].find_all("a"):
-            href = anchor.get('href', '/')
-            if href != "#":
-                page_url.append(href)
-
-    webpage = []
-    for i in page_url:
-        try:
-            page = requests.get(i)
-        except Exception as err:
-            logger.error("Connection error : {0}".format(err))
-            exit(1)
-        if page.status_code == 200:
-            logger.info("page : {0}".format(i))
-            if i not in webpage:
-                webpage.append(i)
-            soup = BeautifulSoup(page.text, 'html.parser')
-            class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline")
-            if len(class_div) > 0:
-                pagingfirstline = class_div[0].find_all("a")
-                if len(pagingfirstline) > 1:
-                    lastpage = pagingfirstline[len(pagingfirstline)-1].get("href", "/")
-                    element_lastpage = lastpage.split("/")[len(lastpage.split("/"))-1]
-                    number_page = element_lastpage.split("-")[0].split("p")[1]
-                    number_lastpage = int(number_page) / 10
-                    for j in range(1,int(number_lastpage)):
-                        paging = j * 10
-                        categorie = urlparse(i).path.split("/")
-                        url_paging = "{0}/archives/p{1}-10.html".format(url, paging)
-                        if len(categorie) > 2:
-                            url_paging = "{0}/archives/{1}/p{2}-10.html".format(url, categorie[2], paging)
-                        logger.info(url_paging)
-                        if url_paging not in webpage:
-                            webpage.append(url_paging)
-                        page = requests.get(url_paging)
-                        if page.status_code == 200:
-                            soup = BeautifulSoup(page.text, 'html.parser')
-                            h2 = soup.find_all("h2")
-                            for title in h2:
-                                href = title.find_all("a")[0].get("href", "/")
-                                if href not in webpage:
-                                    try:
-                                        o = urlparse(href)
-                                        o = o._replace(scheme="https").geturl()
-                                    except Exception as err:
-                                        logger.error("parsing error : {0}".format(err))
-                                        exit(1)
-                                    webpage.append(o)
-    return webpage
-
-
-def downloadPage(webpage, backup_dir, logger):
-   
-    for i in range(0, len(webpage)):
-        try:
-            o = urlparse(webpage[i])
-        except Exception as err:
-            logger.error("parsing error : {0}".format(err))
-            exit(1)
-        path_web = o.path.split("/")
-        filePageWeb = path_web[len(path_web)-1]
-        path_web.pop(len(path_web)-1)
-        dir_page_web = "/".join(path_web)
-        mkdirPath("{0}/{1}/{2}".format(backup_dir, o.netloc, dir_page_web), logger)
-        try:
-            r = requests.get(webpage[i])
-        except Exception as err:
-            logger.error("Connection error : {0}".format(err))
-            exit(1)
-        if r.status_code == 200:
-            fileDownload = "{0}/{1}/index.html".format(backup_dir, o.netloc)
-            if len(dir_page_web) > 0 and len(filePageWeb) > 0:
-                fileDownload = "{0}/{1}{2}/{3}".format(backup_dir, o.netloc, dir_page_web, filePageWeb)
-            logger.info("{0}/{1} : {2}".format(i+1, len(webpage), fileDownload))
-            try:
-                open(fileDownload, "wb").write(r.content)
-            except Exception as err:
-                logger.error("file error : {0}".format(err))
-                exit(1)
-
-
-if __name__ == '__main__':
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--url", help="canblog URL to be scraping", required=True)
-    parser.add_argument("--dir",
-                      default="backup",
-                      help="backup file path")
-    parser.add_argument("--debug", help="Verbosity",  action="store_true")
-    parser.add_argument("--logfile", help="Log file",  default="")
-    parser.add_argument("--no-css", help="No CSS", dest="css",  action="store_true")
-    parser.add_argument("--no-js", help="No JS", dest="js",  action="store_true")
-    parser.add_argument("--no-img", help="No img", dest="img",  action="store_true")
-    parser.add_argument("--no-html", help="No HTML", dest="html", action="store_true")
-    parser.add_argument("--quiet", help="No console output", action="store_true")
-    args = parser.parse_args()
-    logger = logging.getLogger('web_scrap')
-    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-
-    if args.quiet is False:
-        ch = logging.StreamHandler()
-        if args.debug is True:
-            logger.setLevel(logging.DEBUG)
-            ch.setLevel(logging.DEBUG)
-        else:
-            logger.setLevel(logging.INFO)
-            ch.setLevel(logging.INFO)
-        ch.setFormatter(formatter)
-        logger.addHandler(ch)
-
-
-    if len(args.logfile) > 0:
-        fileHandler = logging.FileHandler(args.logfile)
-        if args.debug is True:
-            fileHandler.setLevel(logging.DEBUG)
-        else:
-            fileHandler.setLevel(logging.INFO)
-        fileHandler.setFormatter(formatter)
-        logger.addHandler(fileHandler)
-    
-    try:
-        o = urlparse(args.url)
-        o = o._replace(scheme="https")
-        url = o.geturl().replace(":///", "://")
-    except Exception as err:
-        logger.error("parsing error : {0}".format(err))
-    if args.js is False:
-        script = getScriptCss(url, True, False, logger)
-        downloadPage(script, "{0}/{1}/{2}".format(args.dir, o.path, "dists/js"), logger)
-    
-    if args.css is False:
-        css = getScriptCss(url, False, True, logger)
-        downloadPage(css, "{0}/{1}/{2}".format(args.dir, o.path, "dists/css"), logger)
-    
-    if args.html is False or args.img is False:
-        webpage = getUrlPage(url, logger)
-    if args.html is False:
-        downloadPage(webpage, args.dir, logger)
-    
-    if args.img is False:
-        page_src = getImg(webpage, logger)
-        downloadPage(page_src, "{0}/{1}/{2}".format(args.dir, o.path, "img"), logger)