New upstream version 2020.06.16

[youtubedl] / youtube_dl / extractor / chaturbate.py

diff --git a/youtube_dl/extractor/chaturbate.py b/youtube_dl/extractor/chaturbate.py
index 242fba311fd10380cf7ed4b67e3074eddc279cb2..a459dcb8d5fbedc00f068da023392f0898d687a2 100644 (file)
--- a/youtube_dl/extractor/chaturbate.py
+++ b/youtube_dl/extractor/chaturbate.py
@@ -1,11 +1,17 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import (
+    ExtractorError,
+    lowercase_escape,
+    url_or_none,
+)
 
 
 class ChaturbateIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?chaturbate\.com/(?:fullvideo/?\?.*?\bb=)?(?P<id>[^/?&#]+)'
     _TESTS = [{
         'url': 'https://www.chaturbate.com/siswet19/',
         'info_dict': {
@@ -17,7 +23,11 @@ class ChaturbateIE(InfoExtractor):
         },
         'params': {
             'skip_download': True,
-        }
+        },
+        'skip': 'Room is offline',
+    }, {
+        'url': 'https://chaturbate.com/fullvideo/?b=caylin',
+        'only_matching': True,
     }, {
         'url': 'https://en.chaturbate.com/siswet19/',
         'only_matching': True,
@@ -28,31 +38,71 @@ class ChaturbateIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(url, video_id)
+        webpage = self._download_webpage(
+            'https://chaturbate.com/%s/' % video_id, video_id,
+            headers=self.geo_verification_headers())
+
+        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_url = self._search_regex(
-            r'src=(["\'])(?P<url>http.+?\.m3u8.*?)\1', webpage,
-            'playlist', default=None, 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_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:
-                if any(p not in webpage for p in (
+                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')
 
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
+        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
+            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)
 
         return {
             'id': video_id,
             'title': self._live_title(video_id),
-            'thumbnail': 'https://cdn-s.highwebmedia.com/uHK3McUtGCG3SMFcd4ZJsRv8/roomimage/%s.jpg' % video_id,
+            'thumbnail': 'https://roomimg.stream.highwebmedia.com/ri/%s.jpg' % video_id,
             'age_limit': self._rta_search(webpage),
             'is_live': True,
             'formats': formats,