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

fix import album

Browse Source
This commit is contained in:
Valentin CZERYBA 2023-09-11 23:20:22 +02:00
parent 41e192f903
commit dbab60c7dc
1 changed files with 11 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
lib/WPImport.py
View File

@ -141,7 +141,7 @@ class WPimport:
def _getInfoAlbum(self, link): def _getInfoAlbum(self, link):
if self._ssl_canalblog: if self._ssl_canalblog:
link = link.replace("http", "https") link = link.replace("http", "https").("httpss", "https")
self._logger.info("{0} : Info album : {1}".format(self._name, link)) self._logger.info("{0} : Info album : {1}".format(self._name, link))
link_o = urlparse(link) link_o = urlparse(link)
if len(link_o.netloc) > 0: if len(link_o.netloc) > 0:
@ -162,14 +162,16 @@ class WPimport:
if os.path.exists("{0}/..{1}".format(self._directory, link_o)): if os.path.exists("{0}/..{1}".format(self._directory, link_o)):
page_img = open("{0}/..{1}".format(self._directory, link_o), "r") page_img = open("{0}/..{1}".format(self._directory, link_o), "r")
soup = BeautifulSoup(page_img, self._parser) soup = BeautifulSoup(page_img, self._parser)
paragraph = soup.find("div", class_="albumbody").find("p") paragraphs = soup.find("div", class_="albumbody").find_all("p")
self._logger.info("{0} get paragraph : {1}".format(self._name, paragraph)) for paragraph in paragraphs:
split_paragraph = str(paragraph).split("<br>") self._logger.info("{0} get paragraph : {1}".format(self._name, paragraph))
self._logger.info("{0} length paragraph splitted : {1}".format(self._name, len(split_paragraph))) split_paragraph = str(paragraph).split("<br>")
if len(split_paragraph) == 1: self._logger.info("{0} length paragraph splitted : {1}".format(self._name, len(split_paragraph)))
split_paragraph = str(paragraph).split("<br/>") if len(split_paragraph) == 1:
self._logger.info("{0} get paragraph splitted : {1}".format(self._name, split_paragraph)) split_paragraph = str(paragraph).split("<br/>")
author = split_paragraph[1].split(":")[1].replace(" ", "").lower() self._logger.info("{0} get paragraph splitted : {1}".format(self._name, split_paragraph))
if len(split_paragraph) > 0:
author = split_paragraph[1].split(":")[1].replace(" ", "").lower()
return author return author