1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-05 00:17:43 +00:00
youtube-dl/youtube_dl/extractor/chaturbate.py

110 lines
3.8 KiB
Python
Raw Normal View History

from __future__ import unicode_literals
2015-10-06 21:28:58 +00:00
2017-01-21 13:00:38 +00:00
import re
2015-10-06 21:28:58 +00:00
from .common import InfoExtractor
from ..utils import (
ExtractorError,
lowercase_escape,
url_or_none,
)
2015-10-06 21:28:58 +00:00
class ChaturbateIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://www.chaturbate.com/siswet19/',
'info_dict': {
'id': 'siswet19',
'ext': 'mp4',
'title': 're:^siswet19 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'age_limit': 18,
'is_live': True,
},
'params': {
'skip_download': True,
2016-08-08 05:06:02 +00:00
},
'skip': 'Room is offline',
}, {
'url': 'https://chaturbate.com/fullvideo/?b=caylin',
'only_matching': True,
}, {
'url': 'https://en.chaturbate.com/siswet19/',
'only_matching': True,
}]
2015-10-06 21:28:58 +00:00
_ROOM_OFFLINE = 'Room is currently offline'
2015-10-06 21:28:58 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://chaturbate.com/%s/' % video_id, video_id,
headers=self.geo_verification_headers())
2015-10-06 21:28:58 +00:00
found_m3u8_urls = []
data = self._parse_json(
self._search_regex(
r'initialRoomDossier\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
webpage, 'data', default='{}', group='value'),
video_id, transform_source=lowercase_escape, fatal=False)
if data:
m3u8_url = url_or_none(data.get('hls_source'))
if m3u8_url:
found_m3u8_urls.append(m3u8_url)
if not found_m3u8_urls:
for m in re.finditer(
r'(\\u002[27])(?P<url>http.+?\.m3u8.*?)\1', webpage):
found_m3u8_urls.append(lowercase_escape(m.group('url')))
if not found_m3u8_urls:
for m in re.finditer(
r'(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage):
found_m3u8_urls.append(m.group('url'))
m3u8_urls = []
for found_m3u8_url in found_m3u8_urls:
m3u8_fast_url, m3u8_no_fast_url = found_m3u8_url, found_m3u8_url.replace('_fast', '')
for m3u8_url in (m3u8_fast_url, m3u8_no_fast_url):
if m3u8_url not in m3u8_urls:
m3u8_urls.append(m3u8_url)
if not m3u8_urls:
error = self._search_regex(
[r'<span[^>]+class=(["\'])desc_span\1[^>]*>(?P<error>[^<]+)</span>',
r'<div[^>]+id=(["\'])defchat\1[^>]*>\s*<p><strong>(?P<error>[^<]+)<'],
webpage, 'error', group='error', default=None)
if not error:
2017-01-21 13:00:38 +00:00
if any(p in webpage for p in (
self._ROOM_OFFLINE, 'offline_tipping', 'tip_offline')):
error = self._ROOM_OFFLINE
if error:
raise ExtractorError(error, expected=True)
raise ExtractorError('Unable to find stream URL')
2015-10-06 21:28:58 +00:00
2017-01-21 13:00:38 +00:00
formats = []
for m3u8_url in m3u8_urls:
for known_id in ('fast', 'slow'):
if '_%s' % known_id in m3u8_url:
m3u8_id = known_id
break
else:
m3u8_id = None
2017-01-21 20:00:10 +00:00
formats.extend(self._extract_m3u8_formats(
m3u8_url, video_id, ext='mp4',
# ffmpeg skips segments for fast m3u8
preference=-10 if m3u8_id == 'fast' else None,
m3u8_id=m3u8_id, fatal=False, live=True))
self._sort_formats(formats)
2015-10-06 21:28:58 +00:00
return {
'id': video_id,
'title': self._live_title(video_id),
2017-01-21 13:00:38 +00:00
'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
'age_limit': self._rta_search(webpage),
2015-10-06 21:28:58 +00:00
'is_live': True,
'formats': formats,
}