Backup_Repos/leech
1
0
Fork 0
mirror of https://github.com/kemayo/leech synced 2025-12-25 01:35:38 +01:00
Code Issues Projects Releases Wiki Activity

Royalroad domain name fiddliness

Browse source
This commit is contained in:
David Lynch 2018-08-29 23:07:06 -05:00
parent 72f8fbd6ba
commit 17cd0ea4e2
1 changed files with 12 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
sites/royalroad.py
View file

@ -12,17 +12,19 @@ logger = logging.getLogger(__name__)
@register
class RoyalRoad(Site):
domain = r'royalroad'
"""Royal Road: a place where people write novels, mostly seeming to be light-novel in tone."""
@staticmethod
def matches(url):
# e.g. https://royalroadl.com/fiction/6752/lament-of-the-fallen
match = re.match(r'^(https?://(?:www\.)?royalroadl\.com/fiction/\d+)/?.*', url)
@classmethod
def matches(cls, url):
# e.g. https://royalroad.com/fiction/6752/lament-of-the-fallen
match = re.match(r'^(https?://(?:www\.)?%s\.com/fiction/\d+)/?.*' % cls.domain, url)
if match:
return match.group(1) + '/'
def extract(self, url):
workid = re.match(r'^https?://(?:www\.)?royalroadl\.com/fiction/(\d+)/?.*', url).group(1)
soup = self._soup('https://www.royalroadl.com/fiction/{}'.format(workid))
workid = re.match(r'^https?://(?:www\.)?%s\.com/fiction/(\d+)/?.*' % self.domain, url).group(1)
soup = self._soup('https://www.{}.com/fiction/{}'.format(self.domain, workid))
# should have gotten redirected, for a valid title
original_maxheaders = http.client._MAXHEADERS
@ -58,3 +60,7 @@ class RoyalRoad(Site):
)
return (author_note and (author_note.prettify() + '<hr/>') or '') + content.prettify(), updated
@register
class RoyalRoadL(RoyalRoad):
domain = 'royalroadl'