[extractor/bitchute] Improve BitChuteChannelIE (#5066)

Authored by: flashdagger, pukkandan

yt_dlp/extractor/_extractors.py

@@ -255,6 +255,7 @@
     CamdemyFolderIE
 )
 from .cammodels import CamModelsIE
+from .camsoda import CamsodaIE
 from .camtasia import CamtasiaEmbedIE
 from .camwithher import CamWithHerIE
 from .canalalpha import CanalAlphaIE
@@ -699,6 +700,7 @@
     HotStarIE,
     HotStarPrefixIE,
     HotStarPlaylistIE,
+    HotStarSeasonIE,
     HotStarSeriesIE,
 )
 from .howcast import HowcastIE

yt_dlp/extractor/bitchute.py

@@ -1,14 +1,18 @@
-import itertools
+import functools
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     HEADRequest,
+    OnDemandPagedList,
     clean_html,
     get_element_by_class,
+    get_elements_html_by_class,
     int_or_none,
     orderedSet,
+    parse_count,
+    parse_duration,
     traverse_obj,
     unified_strdate,
     urlencode_postdata,
@@ -109,51 +113,103 @@ def _real_extract(self, url):
 
 
 class BitChuteChannelIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?bitchute\.com/channel/(?P<id>[^/?#&]+)'
-    _TEST = {
-        'url': 'https://www.bitchute.com/channel/victoriaxrave/',
-        'playlist_mincount': 185,
+    _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?P<type>channel|playlist)/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.bitchute.com/channel/bitchute/',
         'info_dict': {
-            'id': 'victoriaxrave',
+            'id': 'bitchute',
+            'title': 'BitChute',
+            'description': 'md5:5329fb3866125afa9446835594a9b138',
         },
-    }
+        'playlist': [
+            {
+                'md5': '7e427d7ed7af5a75b5855705ec750e2b',
+                'info_dict': {
+                    'id': 'UGlrF9o9b-Q',
+                    'ext': 'mp4',
+                    'filesize': None,
+                    'title': 'This is the first video on #BitChute !',
+                    'description': 'md5:a0337e7b1fe39e32336974af8173a034',
+                    'thumbnail': r're:^https?://.*\.jpg$',
+                    'uploader': 'BitChute',
+                    'upload_date': '20170103',
+                    'duration': 16,
+                    'view_count': int,
+                },
+            }
+        ],
+        'params': {
+            'skip_download': True,
+            'playlist_items': '-1',
+        },
+    }, {
+        'url': 'https://www.bitchute.com/playlist/wV9Imujxasw9/',
+        'playlist_mincount': 20,
+        'info_dict': {
+            'id': 'wV9Imujxasw9',
+            'title': 'Bruce MacDonald and "The Light of Darkness"',
+            'description': 'md5:04913227d2714af1d36d804aa2ab6b1e',
+        }
+    }]
 
     _TOKEN = 'zyG6tQcGPE5swyAEFLqKUwMuMMuF6IO2DZ6ZDQjGfsL0e4dcTLwqkTTul05Jdve7'
+    PAGE_SIZE = 25
+    HTML_CLASS_NAMES = {
+        'channel': {
+            'container': 'channel-videos-container',
+            'title': 'channel-videos-title',
+            'description': 'channel-videos-text',
+        },
+        'playlist': {
+            'container': 'playlist-video',
+            'title': 'title',
+            'description': 'description',
+        }
 
-    def _entries(self, channel_id):
-        channel_url = 'https://www.bitchute.com/channel/%s/' % channel_id
-        offset = 0
-        for page_num in itertools.count(1):
-            data = self._download_json(
-                '%sextend/' % channel_url, channel_id,
-                'Downloading channel page %d' % page_num,
-                data=urlencode_postdata({
-                    'csrfmiddlewaretoken': self._TOKEN,
-                    'name': '',
-                    'offset': offset,
-                }), headers={
-                    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
-                    'Referer': channel_url,
-                    'X-Requested-With': 'XMLHttpRequest',
-                    'Cookie': 'csrftoken=%s' % self._TOKEN,
-                })
-            if data.get('success') is False:
-                break
-            html = data.get('html')
-            if not html:
-                break
-            video_ids = re.findall(
-                r'class=["\']channel-videos-image-container[^>]+>\s*<a\b[^>]+\bhref=["\']/video/([^"\'/]+)',
-                html)
-            if not video_ids:
-                break
-            offset += len(video_ids)
-            for video_id in video_ids:
-                yield self.url_result(
-                    'https://www.bitchute.com/video/%s' % video_id,
-                    ie=BitChuteIE.ie_key(), video_id=video_id)
+    }
+
+    @staticmethod
+    def _make_url(playlist_id, playlist_type):
+        return f'https://www.bitchute.com/{playlist_type}/{playlist_id}/'
+
+    def _fetch_page(self, playlist_id, playlist_type, page_num):
+        playlist_url = self._make_url(playlist_id, playlist_type)
+        data = self._download_json(
+            f'{playlist_url}extend/', playlist_id, f'Downloading page {page_num}',
+            data=urlencode_postdata({
+                'csrfmiddlewaretoken': self._TOKEN,
+                'name': '',
+                'offset': page_num * self.PAGE_SIZE,
+            }), headers={
+                'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                'Referer': playlist_url,
+                'X-Requested-With': 'XMLHttpRequest',
+                'Cookie': f'csrftoken={self._TOKEN}',
+            })
+        if not data.get('success'):
+            return
+        classes = self.HTML_CLASS_NAMES[playlist_type]
+        for video_html in get_elements_html_by_class(classes['container'], data.get('html')):
+            video_id = self._search_regex(
+                r'<a\s[^>]*\bhref=["\']/video/([^"\'/]+)', video_html, 'video id', default=None)
+            if not video_id:
+                continue
+            yield self.url_result(
+                f'https://www.bitchute.com/video/{video_id}', BitChuteIE, video_id, url_transparent=True,
+                title=clean_html(get_element_by_class(classes['title'], video_html)),
+                description=clean_html(get_element_by_class(classes['description'], video_html)),
+                duration=parse_duration(get_element_by_class('video-duration', video_html)),
+                view_count=parse_count(clean_html(get_element_by_class('video-views', video_html))))
 
     def _real_extract(self, url):
-        channel_id = self._match_id(url)
+        playlist_type, playlist_id = self._match_valid_url(url).group('type', 'id')
+        webpage = self._download_webpage(self._make_url(playlist_id, playlist_type), playlist_id)
+
+        page_func = functools.partial(self._fetch_page, playlist_id, playlist_type)
         return self.playlist_result(
-            self._entries(channel_id), playlist_id=channel_id)
+            OnDemandPagedList(page_func, self.PAGE_SIZE), playlist_id,
+            title=self._html_extract_title(webpage, default=None),
+            description=self._html_search_meta(
+                ('description', 'og:description', 'twitter:description'), webpage, default=None),
+            playlist_count=int_or_none(self._html_search_regex(
+                r'<span>(\d+)\s+videos?</span>', webpage, 'playlist count', default=None)))

yt_dlp/extractor/camsoda.py

@@ -0,0 +1,59 @@
+import random
+
+from .common import InfoExtractor
+from ..utils import ExtractorError, traverse_obj
+
+
+class CamsodaIE(InfoExtractor):
+    _VALID_URL = r'https?://www\.camsoda\.com/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.camsoda.com/lizzhopf',
+        'info_dict': {
+            'id': 'lizzhopf',
+            'ext': 'mp4',
+            'title': 'lizzhopf (lizzhopf) Nude on Cam. Free Live Sex Chat Room - CamSoda',
+            'description': str,
+            'is_live': True,
+            'age_limit': 18,
+        },
+        'skip': 'Room is offline',
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id, headers=self.geo_verification_headers())
+
+        data = self._download_json(
+            f'https://camsoda.com/api/v1/video/vtoken/{video_id}', video_id,
+            query={'username': f'guest_{random.randrange(10000, 99999)}'},
+            headers=self.geo_verification_headers())
+        if not data:
+            raise ExtractorError('Unable to find configuration for stream.')
+        elif data.get('private_servers'):
+            raise ExtractorError('Model is in private show.', expected=True)
+        elif not data.get('stream_name'):
+            raise ExtractorError('Model is offline.', expected=True)
+
+        stream_name = traverse_obj(data, 'stream_name', expected_type=str)
+        token = traverse_obj(data, 'token', expected_type=str)
+
+        formats = []
+        for server in traverse_obj(data, ('edge_servers', ...)):
+            formats = self._extract_m3u8_formats(
+                f'https://{server}/{stream_name}_v1/index.m3u8?token={token}',
+                video_id, ext='mp4', m3u8_id='hls', fatal=False, live=True)
+            if formats:
+                break
+        if not formats:
+            self.raise_no_formats('No active streams found', expected=True)
+
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': self._html_extract_title(webpage),
+            'description': self._html_search_meta('description', webpage, default=None),
+            'is_live': True,
+            'formats': formats,
+            'age_limit': 18,
+        }

yt_dlp/extractor/hotstar.py

@@ -1,22 +1,19 @@
 import hashlib
 import hmac
+import json
 import re
 import time
 import uuid
-import json
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_HTTPError,
-    compat_str
-)
+from ..compat import compat_HTTPError, compat_str
 from ..utils import (
-    determine_ext,
     ExtractorError,
+    determine_ext,
     int_or_none,
     join_nonempty,
     str_or_none,
-    try_get,
+    traverse_obj,
     url_or_none,
 )
 
@@ -26,6 +23,11 @@ class HotStarBaseIE(InfoExtractor):
     _API_URL = 'https://api.hotstar.com'
     _AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
 
+    def _call_api_v1(self, path, *args, **kwargs):
+        return self._download_json(
+            f'{self._API_URL}/o/v1/{path}', *args, **kwargs,
+            headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'})
+
     def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
         st = int_or_none(st) or int(time.time())
         exp = st + 6000
@@ -59,17 +61,6 @@ def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
                 response['message'], expected=True)
         return response['data']
 
-    def _call_api(self, path, video_id, query_name='contentId'):
-        return self._download_json(
-            f'{self._API_URL}/{path}', video_id=video_id,
-            query={
-                query_name: video_id,
-                'tas': 10000,
-            }, headers={
-                'x-country-code': 'IN',
-                'x-platform-code': 'PCTV',
-            })
-
     def _call_api_v2(self, path, video_id, st=None, cookies=None):
         return self._call_api_impl(
             f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
@@ -79,6 +70,13 @@ def _call_api_v2(self, path, video_id, st=None, cookies=None):
                 'os-version': '10',
             })
 
+    def _playlist_entries(self, path, item_id, root=None, **kwargs):
+        results = self._call_api_v1(path, item_id, **kwargs)['body']['results']
+        for video in traverse_obj(results, (('assets', None), 'items', ...)):
+            if video.get('contentId'):
+                yield self.url_result(
+                    HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])
+
 
 class HotStarIE(HotStarBaseIE):
     IE_NAME = 'hotstar'
@@ -104,6 +102,7 @@ class HotStarIE(HotStarBaseIE):
             'duration': 381,
             'episode': 'Can You Not Spread Rumours?',
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'https://www.hotstar.com/tv/ek-bhram-sarvagun-sampanna/s-2116/janhvi-targets-suman/1000234847',
         'info_dict': {
@@ -161,7 +160,8 @@ def _real_extract(self, url):
         video_type = self._TYPE.get(video_type, video_type)
         cookies = self._get_cookies(url)  # Cookies before any request
 
-        video_data = self._call_api(f'o/v1/{video_type}/detail', video_id)['body']['results']['item']
+        video_data = self._call_api_v1(f'{video_type}/detail', video_id,
+                                       query={'tas': 10000, 'contentId': video_id})['body']['results']['item']
         if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
             self.report_drm(video_id)
 
@@ -258,16 +258,16 @@ class HotStarPrefixIE(InfoExtractor):
         'url': 'hotstar:1000076273',
         'only_matching': True,
     }, {
-        'url': 'hotstar:movies:1000057157',
+        'url': 'hotstar:movies:1260009879',
         'info_dict': {
-            'id': '1000057157',
+            'id': '1260009879',
             'ext': 'mp4',
-            'title': 'Radha Gopalam',
-            'description': 'md5:be3bc342cc120bbc95b3b0960e2b0d22',
-            'timestamp': 1140805800,
-            'upload_date': '20060224',
-            'duration': 9182,
-            'episode': 'Radha Gopalam',
+            'title': 'Nuvvu Naaku Nachav',
+            'description': 'md5:d43701b1314e6f8233ce33523c043b7d',
+            'timestamp': 1567525674,
+            'upload_date': '20190903',
+            'duration': 10787,
+            'episode': 'Nuvvu Naaku Nachav',
         },
     }, {
         'url': 'hotstar:episode:1000234847',
@@ -289,7 +289,7 @@ def _real_extract(self, url):
 
 class HotStarPlaylistIE(HotStarBaseIE):
     IE_NAME = 'hotstar:playlist'
-    _VALID_URL = r'https?://(?:www\.)?hotstar\.com/tv/[^/]+/s-\w+/list/[^/]+/t-(?P<id>\w+)'
+    _VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/tv(?:/[^/]+){2}/list/[^/]+/t-(?P<id>\w+)'
     _TESTS = [{
         'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
         'info_dict': {
@@ -299,22 +299,49 @@ class HotStarPlaylistIE(HotStarBaseIE):
     }, {
         'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
         'only_matching': True,
+    }, {
+        'url': 'https://www.hotstar.com/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        playlist_id = self._match_id(url)
+        id_ = self._match_id(url)
+        return self.playlist_result(
+            self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_)
 
-        collection = self._call_api('o/v1/tray/find', playlist_id, 'uqId')['body']['results']
-        entries = [
-            self.url_result(HotStarIE._video_url(video['contentId']), HotStarIE, video['contentId'])
-            for video in collection['assets']['items'] if video.get('contentId')]
 
-        return self.playlist_result(entries, playlist_id)
+class HotStarSeasonIE(HotStarBaseIE):
+    IE_NAME = 'hotstar:season'
+    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/tv/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028',
+        'info_dict': {
+            'id': '8028',
+        },
+        'playlist_mincount': 35,
+    }, {
+        'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357',
+        'info_dict': {
+            'id': '4357',
+        },
+        'playlist_mincount': 30,
+    }, {
+        'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/',
+        'info_dict': {
+            'id': '8208',
+        },
+        'playlist_mincount': 19,
+    }]
+
+    def _real_extract(self, url):
+        url, season_id = self._match_valid_url(url).groups()
+        return self.playlist_result(self._playlist_entries(
+            'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)
 
 
 class HotStarSeriesIE(HotStarBaseIE):
     IE_NAME = 'hotstar:series'
-    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/tv/[^/]+/(?P<id>\d+))'
+    _VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/tv/[^/]+/(?P<id>\d+))/?(?:[#?]|$)'
     _TESTS = [{
         'url': 'https://www.hotstar.com/in/tv/radhakrishn/1260000646',
         'info_dict': {
@@ -332,22 +359,13 @@ class HotStarSeriesIE(HotStarBaseIE):
         'info_dict': {
             'id': '435',
         },
-        'playlist_mincount': 269,
+        'playlist_mincount': 267,
     }]
 
     def _real_extract(self, url):
         url, series_id = self._match_valid_url(url).groups()
-        headers = {
-            'x-country-code': 'IN',
-            'x-platform-code': 'PCTV',
-        }
-        detail_json = self._download_json(
-            f'{self._API_URL}/o/v1/show/detail?contentId={series_id}', series_id, headers=headers)
-        id = try_get(detail_json, lambda x: x['body']['results']['item']['id'], int)
-        item_json = self._download_json(
-            f'{self._API_URL}/o/v1/tray/g/1/items?etid=0&tao=0&tas=10000&eid={id}', series_id, headers=headers)
+        id_ = self._call_api_v1(
+            'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
 
-        return self.playlist_result([
-            self.url_result(HotStarIE._video_url(video['contentId'], root=url), HotStarIE, video['contentId'])
-            for video in item_json['body']['results']['items'] if video.get('contentId')
-        ], series_id)
+        return self.playlist_result(self._playlist_entries(
+            'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)

yt_dlp/utils.py

@@ -418,6 +418,8 @@ def get_elements_text_and_html_by_attribute(attribute, value, html, *, tag=r'[\w
     Return the text (content) and the html (whole) of the tag with the specified
     attribute in the passed HTML document
     """
+    if not value:
+        return
 
     quote = '' if re.match(r'''[\s"'`=<>]''', value) else '?'