web_scrap/import_export_canalblog.py
2023-05-15 23:51:45 +02:00

270 lines
11 KiB
Python

#!/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):
removeWp = WPRemove(basic=basic, wordpress="", logger=logger)
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):
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)
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):
canalblog = canalblog.split(",")
wordpress = wordpress.split(",")
name = "Thread-{0}".format(int(name_thread) + 1)
if serial is False:
for canal in canalblog:
try:
o = urlparse(canal)
o = o._replace(scheme="https")
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)
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)
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="https")
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)
webpage = exportWp.getUrlPage(name_thread, max_thread)
del exportWp
importWp = WPimport(name=name, basic=basic, wordpress=wordpress[i], logger=logger, parser=parser)
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):
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)
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)
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)
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')
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)
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)
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)
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)
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)
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(",")
exportWp = WPExport(logger=logger, parser=args.parser, directory=args.directory)
for canal in canalblog:
try:
o = urlparse(canal)
o = o._replace(scheme="https")
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)
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)
exit(0)