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

separate article and page

Browse Source
This commit is contained in:
Valentin CZERYBA 2023-05-07 09:26:48 +02:00
parent 21d2f35e6e
commit f9be6770e3
3 changed files with 26 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitignore vendored
View File

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

22
import_export_canalblog.py
View File

@ -3,23 +3,27 @@ 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
def download(name_thread, max_thread, url, logger, parser, directory, html, img):
exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, directory=directory)
exportWp = WPExport(name="Thread-{0}".format(int(name_thread) + 1), url=url, logger=logger, parser=parser, directory=directory)
webpage = exportWp.getUrlPage(name_thread, max_thread)
if html is False:
exportWp.downloadHTML(webpage)
if args.img is False:
exportWp.downloadImg(webpage)
del exportWp
exportWp.downloadHTML(webpage["article"])
exportWp.downloadHTML(webpage["page"])
if img is False:
exportWp.downloadImg(webpage["article"])
exportWp.downloadImg(webpage["page"])
def importUrl(name_thread, max_thread, canalblog, logger, parser, wordpress, basic, serial):
canalblog = canalblog.split(",")
@ -198,6 +202,8 @@ if __name__ == '__main__':
if args.css is False:
exportWp.downloadCss()
del exportWp
if args.html is False or args.img is False:
try:

20
lib/WPExport.py
View File

@ -13,6 +13,7 @@ class WPExport:
self._dir = directory
self._name = name
self._request = requests.Session()
retries = Retry(total=10,
@ -27,6 +28,7 @@ class WPExport:
# Public method
# Set name
def setName(self, name):
@ -83,8 +85,8 @@ class WPExport:
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 = {"page":[], "article":[]}
webpage = []
for i in page_url:
try:
page = self._request.get(i)
@ -93,8 +95,8 @@ class WPExport:
exit(1)
if page.status_code == 200:
self._logger.info("{0} : page : {1}".format(self._name, i))
if i not in webpage:
webpage.append(i)
if i not in webpage["page"]:
webpage["page"].append(i)
soup = BeautifulSoup(page.text, self._parser)
class_div = pagingfirstline = soup.find_all("div", class_="pagingfirstline")
if len(class_div) > 0:
@ -120,27 +122,27 @@ class WPExport:
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:
webpage.append(url_paging)
if url_paging not in webpage["page"]:
webpage["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")
for title in h2:
href = title.find_all("a")[0].get("href", "/")
if href not in webpage:
if href not in webpage["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.append(o)
webpage["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(page.content)
self._logger.debug("{0} : {1}".format(self._name, page.content))
return webpage
# Private method