Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2025-12-06 08:52:55 +01:00
Code Issues Projects Releases Wiki Activity

Merge pull request #689 from AlexRiina/adapter-novelfull-2

Browse source 
add more story meta-data and fix more extra chapter headings
This commit is contained in:
Jim Miller 2021-04-20 19:15:26 -05:00 committed by GitHub
commit ef7ba42f9a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
fanficfare/adapters/adapter_novelfull.py
View file

@ -21,7 +21,17 @@ class NovelFullSiteAdapter(BaseSiteAdapter):
return "novelfull.com" return "novelfull.com"
def getSiteURLPattern(self): def getSiteURLPattern(self):
return r"https?://%s/(?P<name>.+).html?" % re.escape(self.getSiteDomain()) return r"https?://%s/(index\.php/)?(?P<story_id>.+?)(/.*)?\.html?" % re.escape(self.getSiteDomain())
def __init__(self, configuration, url):
super(NovelFullSiteAdapter, self).__init__(configuration, url)
story_id = re.match(self.getSiteURLPattern(), url).group('story_id')
self.story.setMetadata('storyId', story_id)
self._setURL("https://%s/%s.html" % (self.getSiteDomain(), story_id))
self.story.setMetadata('siteabbrev', 'nvlfl')
def extractChapterUrlsAndMetadata(self): def extractChapterUrlsAndMetadata(self):
data = self.get_request(self.url) data = self.get_request(self.url)
@ -75,7 +85,7 @@ class NovelFullSiteAdapter(BaseSiteAdapter):
content = soup.find(id="chapter-content") content = soup.find(id="chapter-content")
# Remove chapter header if present # Remove chapter header if present
chapter_header = content.find("p", text=re.compile(r"Chapter \d+:")) chapter_header = content.find(["p", "h3"], text=re.compile(r"Chapter \d+:"))
if chapter_header: if chapter_header:
chapter_header.decompose() chapter_header.decompose()