1
0
Fork 0
mirror of https://github.com/blackjack4494/yt-dlc.git synced 2024-12-23 00:07:49 +00:00

[manyvids] Fix extraction (closes #18604, closes #18614)

This commit is contained in:
Sergey M․ 2019-01-01 20:31:48 +07:00
parent 6b688b8942
commit 38d15ba7f9
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -2,12 +2,18 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import (
determine_ext,
int_or_none,
str_to_int,
urlencode_postdata,
)
class ManyVidsIE(InfoExtractor): class ManyVidsIE(InfoExtractor):
_VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)' _VALID_URL = r'(?i)https?://(?:www\.)?manyvids\.com/video/(?P<id>\d+)'
_TEST = { _TESTS = [{
# preview video
'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/', 'url': 'https://www.manyvids.com/Video/133957/everthing-about-me/',
'md5': '03f11bb21c52dd12a05be21a5c7dcc97', 'md5': '03f11bb21c52dd12a05be21a5c7dcc97',
'info_dict': { 'info_dict': {
@ -17,7 +23,18 @@ class ManyVidsIE(InfoExtractor):
'view_count': int, 'view_count': int,
'like_count': int, 'like_count': int,
}, },
} }, {
# full video
'url': 'https://www.manyvids.com/Video/935718/MY-FACE-REVEAL/',
'md5': 'f3e8f7086409e9b470e2643edb96bdcc',
'info_dict': {
'id': '935718',
'ext': 'mp4',
'title': 'MY FACE REVEAL',
'view_count': int,
'like_count': int,
},
}]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
@ -28,12 +45,41 @@ class ManyVidsIE(InfoExtractor):
r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1', r'data-(?:video-filepath|meta-video)\s*=s*(["\'])(?P<url>(?:(?!\1).)+)\1',
webpage, 'video URL', group='url') webpage, 'video URL', group='url')
title = '%s (Preview)' % self._html_search_regex( title = self._html_search_regex(
r'<h2[^>]+class="m-a-0"[^>]*>([^<]+)', webpage, 'title') (r'<span[^>]+class=["\']item-title[^>]+>([^<]+)',
r'<h2[^>]+class=["\']h2 m-0["\'][^>]*>([^<]+)'),
webpage, 'title', default=None) or self._html_search_meta(
'twitter:title', webpage, 'title', fatal=True)
if any(p in webpage for p in ('preview_videos', '_preview.mp4')):
title += ' (Preview)'
mv_token = self._search_regex(
r'data-mvtoken=(["\'])(?P<value>(?:(?!\1).)+)\1', webpage,
'mv token', default=None, group='value')
if mv_token:
# Sets some cookies
self._download_webpage(
'https://www.manyvids.com/includes/ajax_repository/you_had_me_at_hello.php',
video_id, fatal=False, data=urlencode_postdata({
'mvtoken': mv_token,
'vid': video_id,
}), headers={
'Referer': url,
'X-Requested-With': 'XMLHttpRequest'
})
if determine_ext(video_url) == 'm3u8':
formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls')
else:
formats = [{'url': video_url}]
like_count = int_or_none(self._search_regex( like_count = int_or_none(self._search_regex(
r'data-likes=["\'](\d+)', webpage, 'like count', default=None)) r'data-likes=["\'](\d+)', webpage, 'like count', default=None))
view_count = int_or_none(self._html_search_regex( view_count = str_to_int(self._html_search_regex(
r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage, r'(?s)<span[^>]+class="views-wrapper"[^>]*>(.+?)</span', webpage,
'view count', default=None)) 'view count', default=None))
@ -42,7 +88,5 @@ class ManyVidsIE(InfoExtractor):
'title': title, 'title': title,
'view_count': view_count, 'view_count': view_count,
'like_count': like_count, 'like_count': like_count,
'formats': [{ 'formats': formats,
'url': video_url,
}],
} }