etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

[pornhub] Separate and fix playlist extractor (#700)

Browse source 
Closes #680
Authored by: mzbaulhaque
This commit is contained in:
mzbaulhaque 2021-08-15 23:32:48 +06:00 committed by GitHub
parent 7a6742b5f9
commit df2a5633da
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 59 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
yt_dlp/extractor/extractors.py
View file

@ -1044,6 +1044,7 @@
from .pornhub import (
PornHubIE,
PornHubUserIE,
PornHubPlaylistIE,
PornHubPagedVideoListIE,
PornHubUserVideosUploadIE,
)

71
yt_dlp/extractor/pornhub.py
View file

@ -3,6 +3,7 @@
import functools
import itertools
import math
import operator
import re
@ -638,7 +639,7 @@ def _real_extract(self, url):
class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'https?://(?:[^/]+\.)?%s/(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
_VALID_URL = r'https?://(?:[^/]+\.)?%s/(?!playlist/)(?P<id>(?:[^/]+/)*[^/?#&]+)' % PornHubBaseIE._PORNHUB_HOST_RE
_TESTS = [{
'url': 'https://www.pornhub.com/model/zoe_ph/videos',
'only_matching': True,
@ -731,18 +732,6 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
}, {
'url': 'https://www.pornhub.com/video/incategories/60fps-1/hd-porn',
'only_matching': True,
}, {
'url': 'https://www.pornhub.com/playlist/44121572',
'info_dict': {
'id': 'playlist/44121572',
},
'playlist_mincount': 132,
}, {
'url': 'https://www.pornhub.com/playlist/4667351',
'only_matching': True,
}, {
'url': 'https://de.pornhub.com/playlist/4667351',
'only_matching': True,
}, {
'url': 'https://pornhubthbh7ap3u.onion/model/zoe_ph/videos',
'only_matching': True,
@ -770,3 +759,59 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
'url': 'http://pornhubthbh7ap3u.onion/pornstar/jenny-blighe/videos/upload',
'only_matching': True,
}]
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?%s/playlist/(?P<id>[^/?#&]+))' % PornHubBaseIE._PORNHUB_HOST_RE
_TESTS = [{
'url': 'https://www.pornhub.com/playlist/44121572',
'info_dict': {
'id': '44121572',
},
'playlist_count': 77,
}, {
'url': 'https://www.pornhub.com/playlist/4667351',
'only_matching': True,
}, {
'url': 'https://de.pornhub.com/playlist/4667351',
'only_matching': True,
}, {
'url': 'https://de.pornhub.com/playlist/4667351?page=2',
'only_matching': True,
}]
def _entries(self, url, host, item_id):
webpage = self._download_webpage(url, item_id, 'Downloading page 1')
playlist_id = self._search_regex(r'var\s+playlistId\s*=\s*"([^"]+)"', webpage, 'playlist_id')
video_count = int_or_none(
self._search_regex(r'var\s+itemsCount\s*=\s*([0-9]+)\s*\|\|', webpage, 'video_count'))
token = self._search_regex(r'var\s+token\s*=\s*"([^"]+)"', webpage, 'token')
page_count = math.ceil((video_count - 36) / 40.) + 1
page_entries = self._extract_entries(webpage, host)
def download_page(page_num):
note = 'Downloading page {}'.format(page_num)
page_url = 'https://www.{}/playlist/viewChunked'.format(host)
return self._download_webpage(page_url, item_id, note, query={
'id': playlist_id,
'page': page_num,
'token': token,
})
for page_num in range(1, page_count + 1):
if page_num > 1:
webpage = download_page(page_num)
page_entries = self._extract_entries(webpage, host)
if not page_entries:
break
for e in page_entries:
yield e
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
item_id = mobj.group('id')
self._login(host)
return self.playlist_result(self._entries(mobj.group('url'), host, item_id), item_id)