v4l3n71n/web_scrap
1
0
Fork 0
Code Issues Pull Requests Projects Releases 10 Wiki Activity

Merge pull request 'webpage-file' (#20) from webpage-file into master

Browse Source 
Reviewed-on: #20
This commit is contained in:
v4l3n71n 2023-06-26 22:28:26 +00:00
commit b88917127d
3 changed files with 88 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
import_export_canalblog.py
View File

@ -5,7 +5,7 @@ from urllib.parse import urlparse
from concurrent import futures
from concurrent.futures import as_completed, wait, ALL_COMPLETED
import argparse, logging, threading
import argparse, logging, threading, os, glob
from lib.WPImport import WPimport
from lib.WPExport import WPExport
from lib.WPRemove import WPRemove
@ -40,21 +40,21 @@ def remove(index, number, args, basic, logger, ssl_wordpress):
del removeWp
def download(name_thread, max_thread, url, logger, parser, directory, html, img, ssl_canalblog):
def download(name_thread, max_thread, url, logger, parser, directory, html, img, ssl_canalblog, revert, tmp):
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)
if not revert:
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])
exportWp.downloadHTML(j, i)
if img is False:
exportWp.downloadImg(webpage[j][i])
exportWp.downloadImg(j, i)
del exportWp
def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, basic, serial, ssl_wordpress, ssl_canalblog, create, update, image):
def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, basic, serial, ssl_wordpress, ssl_canalblog, create, update, image, revert, tmp):
canalblog = canalblog.split(",")
wordpress = wordpress.split(",")
name = "Thread-{0}".format(int(name_thread) + 1)
@ -70,14 +70,15 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
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)
exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, ssl_canalblog=ssl_canalblog, tmp=tmp)
if not revert:
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, no_create=create, no_update=update, no_image=image)
importWp = WPimport(name=name, basic=basic, wordpress=j, logger=logger, parser=parser, ssl_wordpress=ssl_wordpress, no_create=create, no_update=update, no_image=image, tmp=tmp)
for k in ["article", "page"]:
for l in ["publications", "principal"]:
importWp.fromUrl(webpage[l][k])
importWp.fromUrl(l, k)
del importWp
else:
@ -93,9 +94,10 @@ def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, bas
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)
if not revert:
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, no_create=create, no_update=update, no_image=image)
importWp = WPimport(name=name, basic=basic, wordpress=wordpress[i], logger=logger, parser=parser, ssl_wordpress=ssl_wordpress, no_create=create, no_update=update, no_image=image, tmp=tmp)
for k in ["article", "page"]:
for l in ["publications", "principal"]:
@ -117,7 +119,7 @@ def importDirectory(name_thread, max_thread, directory, logger, parser, wordpres
else:
if len(directory) != len(wordpress):
logger.error("{0} : Error : Number directory is differant than wordpress".format(name))
logger.error("{0} : Error : Number directory is different 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, no_create=create, no_update=update, no_image=image)
@ -134,6 +136,8 @@ if __name__ == '__main__':
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="")
parser.add_argument("--revert", help="Restart a work from stopping work", action="store_true")
parser.add_argument("--tmp", help="directory tmp", default="/tmp/import_export_canablog")
subparsers = parser.add_subparsers(dest="command")
@ -187,8 +191,7 @@ if __name__ == '__main__':
default="",
help="File")
args = parser.parse_args()
logger = logging.getLogger('import export canalblog')
@ -223,6 +226,8 @@ if __name__ == '__main__':
fileHandler.setFormatter(formatter)
logger.addHandler(fileHandler)
os.makedirs(args.tmp, exist_ok=True)
if args.command == "import" or args.command == "remove":
password = args.password
if len(args.password) == 0:
@ -255,8 +260,17 @@ if __name__ == '__main__':
with futures.ThreadPoolExecutor(max_workers=int(args.parallel)) as ex:
wait_for = [ ex.submit(remove, i, args.parallel, args, basic, logger, ssl_wordpress) for i in range(0, int(args.parallel)) ]
wait(wait_for, return_when=ALL_COMPLETED)
if args.revert is True:
files_tmp = glob.glob("{0}/*.json".format(args.tmp))
if len(files_tmp) == 0:
logger.error("Error revert, because files not found")
exit(1)
if len(files_tmp) != int(args.parallel):
for file_r in files_tmp:
os.remove(file_r)
wait_for = [
ex.submit(importUrl, i, int(args.parallel), args.canalblog, logger, args.parser, args.wordpress, basic, args.serial, ssl_wordpress, ssl_canalblog, args.create, args.update, args.image)
ex.submit(importUrl, i, int(args.parallel), args.canalblog, logger, args.parser, args.wordpress, basic, args.serial, ssl_wordpress, ssl_canalblog, args.create, args.update, args.image, args.revert, args.tmp)
for i in range(0, int(args.parallel))
]
@ -294,7 +308,7 @@ if __name__ == '__main__':
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)
ex.submit(download, i, int(args.parallel), url, logger, args.parser, args.directory, args.html, args.img, ssl_canalblog, args.revert, args.tmp)
for i in range(0, int(args.parallel))
]
except Exception as err:

23
lib/WPExport.py
View File

@ -1,12 +1,12 @@
#!/usr/bin/python3
from bs4 import BeautifulSoup
from urllib.parse import urlparse
import requests, os, argparse, logging
import requests, os, argparse, logging, json
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):
def __init__(self, name = "Thread-0", url = "", logger = None, parser = "html.parser", directory = "backup", ssl_canalblog=True, tmp="/tmp/import_export_canablog"):
self._url = url
self._logger = logger
self._parser = parser
@ -22,7 +22,7 @@ class WPExport:
status_forcelist=[429, 500, 502, 503, 504], backoff_factor=2)
self._request.mount('{0}://'.format(self._protocol), HTTPAdapter(max_retries=retries))
self._tmp = tmp
# Destructor
def __del__(self):
@ -57,13 +57,13 @@ class WPExport:
# Download HTML
def downloadHTML(self, webpage):
self._downloadPage(webpage, self._dir)
def downloadHTML(self, first, second):
self._downloadPage(webpage[first][second], self._dir)
# Download Image
def downloadImg(self, webpage):
page_src = self._getImg(webpage)
def downloadImg(self, first, second):
page_src = self._getImg(webpage[first][second])
o = urlparse(self._url)
self._downloadPage(page_src, "{0}/{1}/{2}".format(self._dir, o.path, "img"))
@ -161,7 +161,14 @@ class WPExport:
except Exception as err:
self._logger.error("{0} : Exception error : {1}".format(self._name, err))
exit(1)
return webpage
try:
string_webpage = json.dumps(webpage)
open("{0}/{1}.json".format(self._tmp, self._name), "wt").write(string_webpage)
except Exception as ex:
self._logger.error("{0} : Error for writing webpage : {1}".format(self._name, ex))

62
lib/WPImport.py
View File

@ -8,7 +8,7 @@ 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, no_create=False, no_update=False, no_image=False):
def __init__(self, name="Thread-0", basic=None, wordpress="", logger=None, parser="html.parser", ssl_wordpress=True, no_create=False, no_update=False, no_image=False, tmp="/tmp/import_export_canablog"):
self._name = name
self._basic = basic
self._wordpress = wordpress
@ -28,6 +28,7 @@ class WPimport:
self._no_create = no_create
self._no_update = no_update
self._no_image = no_image
self._tmp = tmp
# Destructor
def __del__(self):
@ -38,26 +39,39 @@ class WPimport:
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])
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))
except ConnectionError as err:
self._logger.error("{0} : Connection error for get url {1} : {2}".format(self._name, webpage[i], err))
exit(1)
except Exception as err:
self._logger.error("{0} : Exception error for get url {1} : {2}".format(self._name, webpage[i], err))
def fromUrl(self, first, second):
try:
with open("{0}/{1}.json".format(self._tmp, self._name)) as file:
webpage_content = json.loads(file.read())
self._logger.debug("{0} : size of webpage : {1}".format(self._name, len(webpage_content)))
webpage = webpage_content[first][second]
for i in range(0, len(webpage)):
try:
r = self._request.get(webpage[i])
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)
del webpage_content[first][second][i]
webpage_content = json.dumps(webpage_content)
open("{0}/{1}.json".format(self._tmp, self._name), "wt").write(webpage_content)
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))
except ConnectionError as err:
self._logger.error("{0} : Connection error for get url {1} : {2}".format(self._name, webpage[i], err))
exit(1)
except IOError as err:
self._logger.error("{0} : Connection error for IO url {1} : {2}".format(self._name, webpage[i], err))
exit(1)
except Exception as err:
self._logger.error("{0} : Exception error for get url {1} : {2}".format(self._name, webpage[i], err))
except Exception as ex:
self._logger.error("{0} : Read file json from tmp : {1}".format(self._name, ex))
def fromDirectory(self, directory="", number_thread=1, max_thread=1):
@ -66,9 +80,13 @@ class WPimport:
directories = self._getDirectories([], "{0}".format(directory))
if len(directories) > 0:
files = self._getFiles(directories)
self.fromFile(files, number_thread, max_thread)
self.fromFile(files=files, number_thread=number_thread, max_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):