dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[pornhub:uservideos:upload] Fix extraction (closes #22619)

This commit is contained in:
Sergey M․ 2019-10-05 21:43:31 +07:00
parent 05446d483d
commit 4bf568d36c
No known key found for this signature in database
GPG Key ID: 2C393E0F18A9236D
1 changed files with 10 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
youtube_dl/extractor/pornhub.py
View File

@ -403,6 +403,15 @@ class PornHubUserIE(PornHubPlaylistBaseIE):
class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE): class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
@staticmethod
def _has_more(webpage):
return re.search(
r'''(?x)
<li[^>]+\bclass=["\']page_next|
<link[^>]+\brel=["\']next|
<button[^>]+\bid=["\']moreDataBtn
''', webpage) is not None
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
host = mobj.group('host') host = mobj.group('host')
@ -411,13 +420,11 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
page = int_or_none(self._search_regex( page = int_or_none(self._search_regex(
r'\bpage=(\d+)', url, 'page', default=None)) r'\bpage=(\d+)', url, 'page', default=None))
page_url = self._make_page_url(url)
entries = [] entries = []
for page_num in (page, ) if page is not None else itertools.count(1): for page_num in (page, ) if page is not None else itertools.count(1):
try: try:
webpage = self._download_webpage( webpage = self._download_webpage(
page_url, item_id, 'Downloading page %d' % page_num, url, item_id, 'Downloading page %d' % page_num,
query={'page': page_num}) query={'page': page_num})
except ExtractorError as e: except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404: if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
@ -547,18 +554,6 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url) if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
else super(PornHubPagedVideoListIE, cls).suitable(url)) else super(PornHubPagedVideoListIE, cls).suitable(url))
def _make_page_url(self, url):
return url
@staticmethod
def _has_more(webpage):
return re.search(
r'''(?x)
<li[^>]+\bclass=["\']page_next|
<link[^>]+\brel=["\']next|
<button[^>]+\bid=["\']moreDataBtn
''', webpage) is not None
class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE): class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)' _VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
@ -572,11 +567,3 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload', 'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
'only_matching': True, 'only_matching': True,
}] }]
def _make_page_url(self, url):
mobj = re.match(self._VALID_URL, url)
return '%s/ajax' % mobj.group('url')
@staticmethod
def _has_more(webpage):
return True