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

Compare commits

base: v4l3n71n:6f78a48e57b3744abd9c2559f689486aa5e2d2c3
Branches Tags
v4l3n71n:master
v4l3n71n:4.0.4
v4l3n71n:4.0.3
v4l3n71n:4.0.2
v4l3n71n:4.0.1
v4l3n71n:4.0.0
v4l3n71n:3.1.0
v4l3n71n:3.0.0
v4l3n71n:2.0.1
v4l3n71n:2.0.0
v4l3n71n:1.0.0
..
compare: v4l3n71n:41e192f903381c805b1ebd097cea994c11f64034
Branches Tags
v4l3n71n:master
v4l3n71n:4.0.4
v4l3n71n:4.0.3
v4l3n71n:4.0.2
v4l3n71n:4.0.1
v4l3n71n:4.0.0
v4l3n71n:3.1.0
v4l3n71n:3.0.0
v4l3n71n:2.0.1
v4l3n71n:2.0.0
v4l3n71n:1.0.0

No commits in common. "6f78a48e57b3744abd9c2559f689486aa5e2d2c3" and "41e192f903381c805b1ebd097cea994c11f64034" have entirely different histories.
6f78a48e57 ... 41e192f903

1 changed files with 9 additions and 11 deletions
Show Stats 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").("httpss", "https") link = link.replace("http", "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:
@ -162,16 +162,14 @@ 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)
paragraphs = soup.find("div", class_="albumbody").find_all("p") paragraph = soup.find("div", class_="albumbody").find("p")
for paragraph in paragraphs: self._logger.info("{0} get paragraph : {1}".format(self._name, paragraph))
self._logger.info("{0} get paragraph : {1}".format(self._name, paragraph)) split_paragraph = str(paragraph).split("<br>")
split_paragraph = str(paragraph).split("<br>") self._logger.info("{0} length paragraph splitted : {1}".format(self._name, len(split_paragraph)))
self._logger.info("{0} length paragraph splitted : {1}".format(self._name, len(split_paragraph))) if len(split_paragraph) == 1:
if len(split_paragraph) == 1: split_paragraph = str(paragraph).split("<br/>")
split_paragraph = str(paragraph).split("<br/>") self._logger.info("{0} get paragraph splitted : {1}".format(self._name, split_paragraph))
self._logger.info("{0} get paragraph splitted : {1}".format(self._name, split_paragraph)) author = split_paragraph[1].split(":")[1].replace(" ", "").lower()
if len(split_paragraph) > 1:
author = split_paragraph[1].split(":")[1].replace(" ", "").lower()
return author return author