add debug

Reviewed-on: #5

backup_canalblog.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+
+TAR=/usr/bin/tar
+PYTHON=/usr/bin/python3
+GZIP=/usr/bin/gzip
+SCRIPTDIR=/home/valentin/script
+WEBSCRAP=${SCRIPTDIR}/web_scrap.py
+URL=www.clarissariviere.com
+DATE=$(date +%Y%m%d)
+DIRECTORY=/home/valentin/backup
+BACKUPDIR=/home/valentin/backup_clarissa
+LIST=${BACKUPDIR}/backup.list
+fileBackup="backup-clarissa-${DATE}"
+LOGFILE=web_scrap.txt
+SENDER="valczebackup@gmail.com"
+if [ $(date +%u) -eq 5 ]; then
+	echo > ${LIST}
+	rm -rf "${BACKUPDIR}/*-incr.tar.gz"
+	fileBackup="${fileBackup}-full"
+	subject="Sauvegarde full"	
+else
+	fileBackup="${fileBackup}-incr"
+	subject="Sauvegarde incremental"
+fi
+subject="${subject} ${URL} ${DATE}"
+echo > ${BACKUPDIR}/${LOGFILE}
+${PYTHON} ${WEBSCRAP} --url ${URL} --dir ${DIRECTORY}  --quiet --logfile ${BACKUPDIR}/${LOGFILE}
+if [ ${?} -ne 0 ]; then
+	subject="${subject} echoue : recuperation page"
+	echo ${subject} | mail -s "${subject}" -A ${BACKUPDIR}/${LOGFILE} ${SENDER}
+	exit 1
+fi
+${TAR} --create --file="${BACKUPDIR}/${fileBackup}.tar" --listed-incremental=${LIST} ${DIRECTORY}
+if [ ${?} -ne 0 ]; then
+	subject="${subject} echoue : archivage page "
+	echo ${subject} | mail -s "${subject}" -A ${BACKUPDIR}/${LOGFILE} ${SENDER}
+	exit 1
+fi
+${GZIP} -f -9 "${BACKUPDIR}/${fileBackup}.tar"
+if [ ${?} -ne 0 ]; then
+	subject="${subject} echoue : compression archive "
+	echo ${subject} | mail -s "${subject}" -A ${BACKUPDIR}/${LOGFILE} ${SENDER}
+	exit 1
+fi
+subject="${subject} OK"
+echo ${subject}| mail -s "${subject}" -A ${BACKUPDIR}/${LOGFILE} ${SENDER}
+exit 0

web_scrap.py

@@ -3,7 +3,7 @@ from bs4 import BeautifulSoup
 from urllib.parse import urlparse
 import requests, os, argparse, logging
 
-def mkdir_path(path_dir, logger):
+def mkdirPath(path_dir, logger):
     if not os.path.exists(path_dir):
         makedir = []
         pathh = path_dir.split("/")
@@ -12,11 +12,88 @@ def mkdir_path(path_dir, logger):
             repath = "/".join(makedir)
             if not os.path.exists(repath):
                 logger.debug("Dossier crée : {0}".format(repath))
-                os.mkdir(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):
-    page = requests.get(url)
+    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')
@@ -28,7 +105,11 @@ def getUrlPage(url, logger):
 
     webpage = []
     for i in page_url:
-        page = requests.get(i)
+        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:
@@ -58,30 +139,44 @@ def getUrlPage(url, logger):
                             for title in h2:
                                 href = title.find_all("a")[0].get("href", "/")
                                 if href not in webpage:
-                                    o = urlparse(href)
-                                    o = o._replace(scheme="https").geturl()
+                                    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(url, backup_dir, logger):
-    o = urlparse(url)
-    o = o._replace(scheme="https")
-    webpage = getUrlPage(o.geturl().replace(":///", "://"), logger)
+def downloadPage(webpage, backup_dir, logger):
+   
     for i in range(0, len(webpage)):
-        o = urlparse(webpage[i])
+        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)
-        mkdir_path("{0}/{1}".format(backup_dir, dir_page_web), logger)
-        r = requests.get(webpage[i])
+        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}/index.html".format(backup_dir)
+            fileDownload = "{0}/{1}/index.html".format(backup_dir, o.netloc)
             if len(dir_page_web) > 0 and len(filePageWeb) > 0:
-                fileDownload = "{0}/{1}/{2}".format(backup_dir, dir_page_web, filePageWeb)
-            logger.info("{0}/{1} : {2}".format(i, len(webpage), fileDownload))
-            open(fileDownload, "wb").write(r.content)
+                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__':
@@ -91,19 +186,56 @@ if __name__ == '__main__':
                       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')
-    ch = logging.StreamHandler()
-
-    if args.debug is not None:
-        logger.setLevel(logging.DEBUG)
-        ch.setLevel(logging.DEBUG)
-    else:
-        logger.setLevel(logging.INFO)
-        ch.setLevel(logging.INFO)
-
     formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
-    ch.setFormatter(formatter)
-    logger.addHandler(ch)
 
-    downloadPage(args.url, args.dir, logger)
+    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)