Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2026-01-01 13:44:48 +01:00
Code Issues Projects Releases Wiki Activity

base_efiction: .string -> stripHTML for nested tags Closes #984

Browse source
This commit is contained in:
Jim Miller 2023-08-05 16:13:57 -05:00
parent fb552c823a
commit 930ba5bb19
1 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
fanficfare/adapters/base_efiction_adapter.py
View file

@ -409,9 +409,9 @@ class BaseEfictionAdapter(BaseSiteAdapter):
pagetitleDiv = soup.find("div", {"id": "pagetitle"})
if pagetitleDiv.find('a') is None:
raise exceptions.FailedToDownload("Couldn't find title and author")
self.story.setMetadata('title', pagetitleDiv.find("a").string)
self.story.setMetadata('title', stripHTML(pagetitleDiv.find("a")))
authorLink = pagetitleDiv.findAll("a")[1]
self.story.setMetadata('author', authorLink.string)
self.story.setMetadata('author', stripHTML(authorLink))
self.story.setMetadata('authorId', re.search(r"\d+", authorLink['href']).group(0))
self.story.setMetadata('authorUrl', self.getViewUserUrl(self.story.getMetadata('authorId')))
@ -431,7 +431,7 @@ class BaseEfictionAdapter(BaseSiteAdapter):
else:
valueStr += unicode(nextEl)
nextEl = nextEl.nextSibling
key = labelSpan.string.strip()
key = stripHTML(labelSpan)
## strip trailing colons
key = re.sub(r"\s*:\s*$", "", key)
@ -467,8 +467,8 @@ class BaseEfictionAdapter(BaseSiteAdapter):
## Had a problem with an author putting <b>0.</b> in the text.
if chapterLink and chapterLink['href'].startswith('#'):
chapterLink['href'] = "%s&chapter=%s" % (self.url, chapterId)
if chapterLink.string != self.getBacktoIndex():
self.add_chapter(chapterLink.string, chapterLink['href'])
if stripHTML(chapterLink) != self.getBacktoIndex():
self.add_chapter(stripHTML(chapterLink), chapterLink['href'])
## Store reference to soup for getChapterText
self.html = soup