Backup_Repos/FanFicFare
1
0
Fork 0
mirror of https://github.com/JimmXinu/FanFicFare.git synced 2025-12-06 17:02:43 +01:00
Code Issues Projects Releases Wiki Activity

adapter_scribblehubcom: Allow for changing title in story URL.

Browse source
This commit is contained in:
Jim Miller 2024-08-14 13:00:33 -05:00
parent 4ea869a764
commit 654619e7e2
2 changed files with 55 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
calibre-plugin/fff_plugin.py
View file

@ -1133,7 +1133,7 @@ class FanFicFarePlugin(InterfaceAction):
## Jul 2024, added similar handling for scribblehub
## https://www.scribblehub.com/series/862913/title
if r"\.scribblehub\.com" in regexp:
regexp = re.sub(r"^(?P<keep>.*com/series/\d+/\d+/)(?P<urltitle>[^\$]*)?",
regexp = re.sub(r"^(?P<keep>.*com/series/\d+/)(?P<urltitle>[^$]*)?",
r"\g<keep>(.*)",regexp)
# logger.debug(regexp)
retval = self.gui.current_db.search_getting_ids(regexp,None,use_virtual_library=False)

60
fanficfare/adapters/adapter_scribblehubcom.py
View file

@ -57,16 +57,9 @@ class ScribbleHubComAdapter(BaseSiteAdapter): # XXX
self.username = "NoneGiven" # if left empty, site doesn't return any message at all.
self.password = ""
self.is_adult=False
self.urltitle = "some-title"
m = re.match(self.getSiteURLPattern(),url)
# logger.debug("id:%s"%m.group('id'))
# logger.debug("title:%s"%m.group('title'))
# get storyId from url
self.story.setMetadata('storyId', m.group('id'))
# normalized story URL.
self._setURL('https://' + self.getSiteDomain() + '/series/' + self.story.getMetadata('storyId') + '/' + m.group('title') + '/')
self.set_story_idurl(url)
# Each adapter needs to have a unique site abbreviation.
self.story.setMetadata('siteabbrev','scrhub') # XXX
@ -75,6 +68,19 @@ class ScribbleHubComAdapter(BaseSiteAdapter): # XXX
# http://docs.python.org/library/datetime.html#strftime-strptime-behavior
self.dateformat = "%b %d, %Y" # XXX
def set_story_idurl(self,url):
m = re.match(self.getSiteURLPattern(),url)
# logger.debug("id:%s"%m.group('id'))
# logger.debug("urltitle:%s"%m.group('urltitle'))
# get storyId from url
self.story.setMetadata('storyId', m.group('id'))
if m.group('urltitle'):
self.urltitle = m.group('urltitle')
# logger.debug("urltitle:%s"%self.urltitle)
# normalized story URL.
self._setURL('https://' + self.getSiteDomain() + '/series/' + self.story.getMetadata('storyId') + '/' + self.urltitle + '/')
@staticmethod # must be @staticmethod, don't remove it.
def getSiteDomain():
@ -88,7 +94,35 @@ class ScribbleHubComAdapter(BaseSiteAdapter): # XXX
return "https://"+cls.getSiteDomain()+"/series/1234/storyname/"
def getSiteURLPattern(self):
return re.escape("https://"+self.getSiteDomain())+r"/(series|read)/(?P<id>\d+)[/-](?P<title>[^/]+)?"
return self._get_site_url_pattern()
## here so getSiteURLPattern and get_section_url(class method) can
## both use it. Note adapter_fictionpresscom has one too.
@classmethod
def _get_site_url_pattern(cls):
return re.escape("https://"+cls.getSiteDomain())+r"/(series|read)/(?P<id>\d+)([/-](?P<urltitle>[^/]+))?"
@classmethod
def get_section_url(cls,url):
## minimal URL used for section names in INI and reject list
## for comparison
# logger.debug("pre section--url:%s"%url)
m = re.match(cls._get_site_url_pattern(),url)
if m:
url = "https://"+cls.getSiteDomain()\
+"/series/"+m.group('id')+"/a-title/"
# logger.debug("post-section url:%s"%url)
return url
## normalized chapter URLs DO contain the story title now, but
## normalized to current urltitle in case of title changes.
def normalize_chapterurl(self,url):
# https://www.scribblehub.com/read/862913-hp-the-arcane-thief-litrpg/chapter/1175961/
# logger.debug("pre normal chapter--url:%s"%url)
url = re.sub(r"https?://(?P<keep>www\.scribblehub\.com/read/\d+-).*(?P<chapter>/chapter/\d+/)",
(r"https://\g<keep>"+self.urltitle+r"\g<chapter>"),url)
# logger.debug("post normal chapter-url:%s"%url)
return url
def post_request(self, url,
parameters=None,
@ -136,11 +170,15 @@ class ScribbleHubComAdapter(BaseSiteAdapter): # XXX
soup = self.make_soup(data)
## Title
pagetitle = soup.find('div',{'class':'fic_title'})
self.story.setMetadata('title',stripHTML(pagetitle))
## <link rel="canonical" href="https://www.scribblehub.com/series/862913/hp-the-arcane-thief-litrpg/" />
canonicalurl = soup.select_one('link[rel=canonical]')['href']
self.set_story_idurl(canonicalurl)
url = canonicalurl
# Find authorid and URL from main story page
self.story.setMetadata('authorId',stripHTML(soup.find('span',{'class':'auth_name_fic'})))
self.story.setMetadata('authorUrl',soup.find('div',{'class':'author'}).find('div',{'property':'author'}).find('span',{'property':'name'}).find('a').get('href'))