projects
/
youtube-dl
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
[youtube] extract more format metadata
[youtube-dl]
/
youtube_dl
/
extractor
/
pornhub.py
diff --git
a/youtube_dl/extractor/pornhub.py
b/youtube_dl/extractor/pornhub.py
index 97f988da4ac249874e7bf47c570a89be5eb9bc8b..e377de19664524844699e4046d3ebe48fcbc0167 100644
(file)
--- a/
youtube_dl/extractor/pornhub.py
+++ b/
youtube_dl/extractor/pornhub.py
@@
-18,6
+18,7
@@
from ..utils import (
orderedSet,
remove_quotes,
str_to_int,
orderedSet,
remove_quotes,
str_to_int,
+ url_or_none,
)
)
@@
-26,7
+27,7
@@
class PornHubIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
_VALID_URL = r'''(?x)
https?://
(?:
- (?:[^/]+\.)?
pornhub\.com
/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+ (?:[^/]+\.)?
(?P<host>pornhub\.(?:com|net))
/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
(?:www\.)?thumbzilla\.com/video/
)
(?P<id>[\da-z]+)
(?:www\.)?thumbzilla\.com/video/
)
(?P<id>[\da-z]+)
@@
-39,6
+40,7
@@
class PornHubIE(InfoExtractor):
'ext': 'mp4',
'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
'uploader': 'Babes',
'ext': 'mp4',
'title': 'Seductive Indian beauty strips down and fingers her pink pussy',
'uploader': 'Babes',
+ 'upload_date': '20130628',
'duration': 361,
'view_count': int,
'like_count': int,
'duration': 361,
'view_count': int,
'like_count': int,
@@
-56,6
+58,7
@@
class PornHubIE(InfoExtractor):
'ext': 'mp4',
'title': '重庆婷婷女王足交',
'uploader': 'Unknown',
'ext': 'mp4',
'title': '重庆婷婷女王足交',
'uploader': 'Unknown',
+ 'upload_date': '20150213',
'duration': 1753,
'view_count': int,
'like_count': int,
'duration': 1753,
'view_count': int,
'like_count': int,
@@
-68,6
+71,31
@@
class PornHubIE(InfoExtractor):
'params': {
'skip_download': True,
},
'params': {
'skip_download': True,
},
+ }, {
+ # subtitles
+ 'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
+ 'info_dict': {
+ 'id': 'ph5af5fef7c2aa7',
+ 'ext': 'mp4',
+ 'title': 'BFFS - Cute Teen Girls Share Cock On the Floor',
+ 'uploader': 'BFFs',
+ 'duration': 622,
+ 'view_count': int,
+ 'like_count': int,
+ 'dislike_count': int,
+ 'comment_count': int,
+ 'age_limit': 18,
+ 'tags': list,
+ 'categories': list,
+ 'subtitles': {
+ 'en': [{
+ "ext": 'srt'
+ }]
+ },
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}, {
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
'only_matching': True,
}, {
'url': 'http://www.pornhub.com/view_video.php?viewkey=ph557bbb6676d2d',
'only_matching': True,
@@
-93,12
+121,15
@@
class PornHubIE(InfoExtractor):
}, {
'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
'only_matching': True,
}, {
'url': 'http://www.pornhub.com/video/show?viewkey=648719015',
'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.net/view_video.php?viewkey=203640933',
+ 'only_matching': True,
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
}]
@staticmethod
def _extract_urls(webpage):
return re.findall(
- r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.
com
/embed/[\da-z]+)',
+ r'<iframe[^>]+?src=["\'](?P<url>(?:https?:)?//(?:www\.)?pornhub\.
(?:com|net)
/embed/[\da-z]+)',
webpage)
def _extract_count(self, pattern, webpage, name):
webpage)
def _extract_count(self, pattern, webpage, name):
@@
-106,14
+137,16
@@
class PornHubIE(InfoExtractor):
pattern, webpage, '%s count' % name, fatal=False))
def _real_extract(self, url):
pattern, webpage, '%s count' % name, fatal=False))
def _real_extract(self, url):
- video_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ host = mobj.group('host') or 'pornhub.com'
+ video_id = mobj.group('id')
- self._set_cookie(
'pornhub.com'
, 'age_verified', '1')
+ self._set_cookie(
host
, 'age_verified', '1')
def dl_webpage(platform):
def dl_webpage(platform):
- self._set_cookie(
'pornhub.com'
, 'platform', platform)
+ self._set_cookie(
host
, 'platform', platform)
return self._download_webpage(
return self._download_webpage(
- 'http://www.
pornhub.com/view_video.php?viewkey=%s' % video_id
,
+ 'http://www.
%s/view_video.php?viewkey=%s' % (host, video_id)
,
video_id, 'Downloading %s webpage' % platform)
webpage = dl_webpage('pc')
video_id, 'Downloading %s webpage' % platform)
webpage = dl_webpage('pc')
@@
-139,12
+172,19
@@
class PornHubIE(InfoExtractor):
video_urls = []
video_urls_set = set()
video_urls = []
video_urls_set = set()
+ subtitles = {}
flashvars = self._parse_json(
self._search_regex(
r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
video_id)
if flashvars:
flashvars = self._parse_json(
self._search_regex(
r'var\s+flashvars_\d+\s*=\s*({.+?});', webpage, 'flashvars', default='{}'),
video_id)
if flashvars:
+ subtitle_url = url_or_none(flashvars.get('closedCaptionsFile'))
+ if subtitle_url:
+ subtitles.setdefault('en', []).append({
+ 'url': subtitle_url,
+ 'ext': 'srt',
+ })
thumbnail = flashvars.get('image_url')
duration = int_or_none(flashvars.get('video_duration'))
media_definitions = flashvars.get('mediaDefinitions')
thumbnail = flashvars.get('image_url')
duration = int_or_none(flashvars.get('video_duration'))
media_definitions = flashvars.get('mediaDefinitions')
@@
-204,8
+244,14
@@
class PornHubIE(InfoExtractor):
video_urls.append((video_url, None))
video_urls_set.add(video_url)
video_urls.append((video_url, None))
video_urls_set.add(video_url)
+ upload_date = None
formats = []
for video_url, height in video_urls:
formats = []
for video_url, height in video_urls:
+ if not upload_date:
+ upload_date = self._search_regex(
+ r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
+ if upload_date:
+ upload_date = upload_date.replace('/', '')
tbr = None
mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
if mobj:
tbr = None
mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
if mobj:
@@
-221,7
+267,7
@@
class PornHubIE(InfoExtractor):
self._sort_formats(formats)
video_uploader = self._html_search_regex(
self._sort_formats(formats)
video_uploader = self._html_search_regex(
- r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:
user|channel)s
/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
+ r'(?s)From: .+?<(?:a\b[^>]+\bhref=["\']/(?:
(?:user|channel)s|model|pornstar)
/|span\b[^>]+\bclass=["\']username)[^>]+>(.+?)<',
webpage, 'uploader', fatal=False)
view_count = self._extract_count(
webpage, 'uploader', fatal=False)
view_count = self._extract_count(
@@
-245,6
+291,7
@@
class PornHubIE(InfoExtractor):
return {
'id': video_id,
'uploader': video_uploader,
return {
'id': video_id,
'uploader': video_uploader,
+ 'upload_date': upload_date,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
@@
-256,11
+303,12
@@
class PornHubIE(InfoExtractor):
'age_limit': 18,
'tags': tags,
'categories': categories,
'age_limit': 18,
'tags': tags,
'categories': categories,
+ 'subtitles': subtitles,
}
class PornHubPlaylistBaseIE(InfoExtractor):
}
class PornHubPlaylistBaseIE(InfoExtractor):
- def _extract_entries(self, webpage):
+ def _extract_entries(self, webpage
, host
):
# Only process container div with main playlist content skipping
# drop-down menu that uses similar pattern for videos (see
# https://github.com/rg3/youtube-dl/issues/11594).
# Only process container div with main playlist content skipping
# drop-down menu that uses similar pattern for videos (see
# https://github.com/rg3/youtube-dl/issues/11594).
@@
-270,7
+318,7
@@
class PornHubPlaylistBaseIE(InfoExtractor):
return [
self.url_result(
return [
self.url_result(
- 'http://www.
pornhub.com/%s' % video_url
,
+ 'http://www.
%s/%s' % (host, video_url)
,
PornHubIE.ie_key(), video_title=title)
for video_url, title in orderedSet(re.findall(
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
PornHubIE.ie_key(), video_title=title)
for video_url, title in orderedSet(re.findall(
r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"',
@@
-278,11
+326,13
@@
class PornHubPlaylistBaseIE(InfoExtractor):
]
def _real_extract(self, url):
]
def _real_extract(self, url):
- playlist_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ host = mobj.group('host')
+ playlist_id = mobj.group('id')
webpage = self._download_webpage(url, playlist_id)
webpage = self._download_webpage(url, playlist_id)
- entries = self._extract_entries(webpage)
+ entries = self._extract_entries(webpage
, host
)
playlist = self._parse_json(
self._search_regex(
playlist = self._parse_json(
self._search_regex(
@@
-297,7
+347,7
@@
class PornHubPlaylistBaseIE(InfoExtractor):
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
- _VALID_URL = r'https?://(?:[^/]+\.)?
pornhub\.com
/playlist/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:[^/]+\.)?
(?P<host>pornhub\.(?:com|net))
/playlist/(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.pornhub.com/playlist/4667351',
'info_dict': {
_TESTS = [{
'url': 'http://www.pornhub.com/playlist/4667351',
'info_dict': {
@@
-312,7
+362,7
@@
class PornHubPlaylistIE(PornHubPlaylistBaseIE):
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
- _VALID_URL = r'https?://(?:[^/]+\.)?
pornhub\.com/(?:user|channel)s
/(?P<id>[^/]+)/videos'
+ _VALID_URL = r'https?://(?:[^/]+\.)?
(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)
/(?P<id>[^/]+)/videos'
_TESTS = [{
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'info_dict': {
_TESTS = [{
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'info_dict': {
@@
-344,10
+394,18
@@
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
}, {
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'only_matching': True,
}, {
'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/model/jayndrea/videos/upload',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.pornhub.com/pornstar/jenny-blighe/videos/upload',
+ 'only_matching': True,
}]
def _real_extract(self, url):
}]
def _real_extract(self, url):
- user_id = self._match_id(url)
+ mobj = re.match(self._VALID_URL, url)
+ host = mobj.group('host')
+ user_id = mobj.group('id')
entries = []
for page_num in itertools.count(1):
entries = []
for page_num in itertools.count(1):
@@
-359,7
+417,7
@@
class PornHubUserVideosIE(PornHubPlaylistBaseIE):
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break
raise
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
break
raise
- page_entries = self._extract_entries(webpage)
+ page_entries = self._extract_entries(webpage
, host
)
if not page_entries:
break
entries.extend(page_entries)
if not page_entries:
break
entries.extend(page_entries)