github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[pornflip] Improve and extract dash formats (closes #11795)

Browse source
This commit is contained in:
Sergey M․ 2017-01-22 03:43:27 +07:00
parent 8d1fbe0cb2
commit 271808b6b2
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 56 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

79
youtube_dl/extractor/pornflip.py
View file

@ -4,56 +4,89 @@
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_str,
)
from ..utils import (
int_or_none,
try_get,
RegexNotFoundError,
unified_timestamp,
)
class PornFlipIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornflip\.com/v/(?P<id>[0-9A-Za-z]{11})'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:v|embed)/(?P<id>[0-9A-Za-z]{11})'
_TESTS = [{
'url': 'https://www.pornflip.com/v/wz7DfNhMmep',
'md5': '98c46639849145ae1fd77af532a9278c',
'info_dict': {
'id': 'wz7DfNhMmep',
'ext': 'mp4',
'title': '2 Amateurs swallow make his dream cumshots true',
'uploader': 'figifoto',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 112,
'timestamp': 1481655502,
'upload_date': '20161213',
'uploader_id': '106786',
'uploader': 'figifoto',
'view_count': int,
'age_limit': 18,
}
}
}, {
'url': 'https://www.pornflip.com/embed/wz7DfNhMmep',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
uploader = self._html_search_regex(
r'<span class="name">\s+<a class="ajax" href=".+>\s+<strong>([^<]+)<', webpage, 'uploader', fatal=False)
flashvars = compat_parse_qs(self._html_search_regex(
r'<embed.+?flashvars="([^"]+)"',
webpage, 'flashvars'))
title = flashvars['video_vars[title]'][0]
thumbnail = try_get(flashvars, lambda x: x['video_vars[big_thumb]'][0])
formats = []
for k, v in flashvars.items():
height = self._search_regex(r'video_vars\[video_urls\]\[(\d+).+?\]', k, 'height', default=None)
if height:
url = v[0]
formats.append({
'height': int_or_none(height),
'url': url
})
webpage = self._download_webpage(
'https://www.pornflip.com/v/%s' % video_id, video_id)
flashvars = compat_parse_qs(self._search_regex(
r'<embed[^>]+flashvars=(["\'])(?P<flashvars>(?:(?!\1).)+)\1',
webpage, 'flashvars', group='flashvars'))
title = flashvars['video_vars[title]'][0]
def flashvar(kind):
return try_get(
flashvars, lambda x: x['video_vars[%s]' % kind][0], compat_str)
formats = []
for key, value in flashvars.items():
if not (value and isinstance(value, list)):
continue
format_url = value[0]
if key == 'video_vars[hds_manifest]':
formats.extend(self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False))
continue
height = self._search_regex(
r'video_vars\[video_urls\]\[(\d+)', key, 'height', default=None)
if not height:
continue
formats.append({
'url': format_url,
'format_id': 'http-%s' % height,
'height': int_or_none(height),
})
self._sort_formats(formats)
uploader = self._html_search_regex(
(r'<span[^>]+class="name"[^>]*>\s*<a[^>]+>\s*<strong>(?P<uploader>[^<]+)',
r'<meta[^>]+content=(["\'])[^>]*\buploaded by (?P<uploader>.+?)\1'),
webpage, 'uploader', fatal=False, group='uploader')
return {
'id': video_id,
'formats': formats,
'title': title,
'thumbnail': flashvar('big_thumb'),
'duration': int_or_none(flashvar('duration')),
'timestamp': unified_timestamp(self._html_search_meta(
'uploadDate', webpage, 'timestamp')),
'uploader_id': flashvar('author_id'),
'uploader': uploader,
'thumbnail': thumbnail,
'view_count': int_or_none(flashvar('views')),
'age_limit': 18,
}