[Alsace20TV] Add new extractors Alsace20TVIE, Alsace20TVEmbedIE

CPACIE: single episode
CPACPlaylistIE: playlists and searches

youtube_dl/extractor/aliexpress.py

@@ -18,7 +18,7 @@ class AliExpressLiveIE(InfoExtractor):
             'id': '2800002704436634',
             'ext': 'mp4',
             'title': 'CASIMA7.22',
-            'thumbnail': r're:http://.*\.jpg',
+            'thumbnail': r're:https?://.*\.jpg',
             'uploader': 'CASIMA Official Store',
             'timestamp': 1500717600,
             'upload_date': '20170722',

youtube_dl/extractor/alsace20tv.py

@@ -0,0 +1,89 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+    clean_html,
+    dict_get,
+    get_element_by_class,
+    int_or_none,
+    unified_strdate,
+    url_or_none,
+)
+
+
+class Alsace20TVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?alsace20\.tv/(?:[\w-]+/)+[\w-]+-(?P<id>[\w]+)'
+    _TESTS = [{
+        'url': 'https://www.alsace20.tv/VOD/Actu/JT/Votre-JT-jeudi-3-fevrier-lyNHCXpYJh.html',
+        # 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
+        'info_dict': {
+            'id': 'lyNHCXpYJh',
+            'ext': 'mp4',
+            'description': 'md5:fc0bc4a0692d3d2dba4524053de4c7b7',
+            'title': 'Votre JT du jeudi 3 février',
+            'upload_date': '20220203',
+            'thumbnail': r're:https?://.+\.jpg',
+            'duration': 1073,
+            'view_count': int,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
+
+    def _extract_video(self, video_id, url=None):
+        info = self._download_json(
+            'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
+            video_id) or {}
+        title = info['titre']
+
+        formats = []
+        for res, fmt_url in (info.get('files') or {}).items():
+            formats.extend(
+                self._extract_smil_formats(fmt_url, video_id, fatal=False)
+                if '/smil:_' in fmt_url
+                else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
+        self._sort_formats(formats)
+
+        webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
+        thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
+        upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
+        upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': clean_html(get_element_by_class('wysiwyg', webpage)),
+            'upload_date': upload_date,
+            'thumbnail': thumbnail,
+            'duration': int_or_none(self._og_search_property('video:duration', webpage) if webpage else None),
+            'view_count': int_or_none(info.get('nb_vues')),
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self._extract_video(video_id, url)
+
+
+class Alsace20TVEmbedIE(Alsace20TVIE):
+    _VALID_URL = r'https?://(?:www\.)?alsace20\.tv/emb/(?P<id>[\w]+)'
+    _TESTS = [{
+        'url': 'https://www.alsace20.tv/emb/lyNHCXpYJh',
+        # 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
+        'info_dict': {
+            'id': 'lyNHCXpYJh',
+            'ext': 'mp4',
+            'title': 'Votre JT du jeudi 3 février',
+            'upload_date': '20220203',
+            'thumbnail': r're:https?://.+\.jpg',
+            'view_count': int,
+        },
+        'params': {
+            'format': 'bestvideo',
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self._extract_video(video_id)

youtube_dl/extractor/bigo.py

@@ -0,0 +1,59 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import ExtractorError, urlencode_postdata
+
+
+class BigoIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?bigo\.tv/(?:[a-z]{2,}/)?(?P<id>[^/]+)'
+
+    _TESTS = [{
+        'url': 'https://www.bigo.tv/ja/221338632',
+        'info_dict': {
+            'id': '6576287577575737440',
+            'title': '土よ〜💁‍♂️ 休憩室/REST room',
+            'thumbnail': r're:https?://.+',
+            'uploader': '✨Shin💫',
+            'uploader_id': '221338632',
+            'is_live': True,
+        },
+        'skip': 'livestream',
+    }, {
+        'url': 'https://www.bigo.tv/th/Tarlerm1304',
+        'only_matching': True,
+    }, {
+        'url': 'https://bigo.tv/115976881',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+
+        info_raw = self._download_json(
+            'https://bigo.tv/studio/getInternalStudioInfo',
+            user_id, data=urlencode_postdata({'siteId': user_id}))
+
+        if not isinstance(info_raw, dict):
+            raise ExtractorError('Received invalid JSON data')
+        if info_raw.get('code'):
+            raise ExtractorError(
+                'Bigo says: %s (code %s)' % (info_raw.get('msg'), info_raw.get('code')), expected=True)
+        info = info_raw.get('data') or {}
+
+        if not info.get('alive'):
+            raise ExtractorError('This user is offline.', expected=True)
+
+        return {
+            'id': info.get('roomId') or user_id,
+            'title': info.get('roomTopic') or info.get('nick_name') or user_id,
+            'formats': [{
+                'url': info.get('hls_src'),
+                'ext': 'mp4',
+                'protocol': 'm3u8',
+            }],
+            'thumbnail': info.get('snapshot'),
+            'uploader': info.get('nick_name'),
+            'uploader_id': user_id,
+            'is_live': True,
+        }

youtube_dl/extractor/cpac.py

@@ -0,0 +1,148 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    str_or_none,
+    try_get,
+    unified_timestamp,
+    update_url_query,
+    urljoin,
+)
+
+# compat_range
+try:
+    if callable(xrange):
+        range = xrange
+except (NameError, TypeError):
+    pass
+
+
+class CPACIE(InfoExtractor):
+    IE_NAME = 'cpac'
+    _VALID_URL = r'https?://(?:www\.)?cpac\.ca/(?P<fr>l-)?episode\?id=(?P<id>[\da-f]{8}(?:-[\da-f]{4}){3}-[\da-f]{12})'
+    _TEST = {
+        # 'url': 'http://www.cpac.ca/en/programs/primetime-politics/episodes/65490909',
+        'url': 'https://www.cpac.ca/episode?id=fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
+        'md5': 'e46ad699caafd7aa6024279f2614e8fa',
+        'info_dict': {
+            'id': 'fc7edcae-4660-47e1-ba61-5b7f29a9db0f',
+            'ext': 'mp4',
+            'upload_date': '20220215',
+            'title': 'News Conference to Celebrate National Kindness Week – February 15, 2022',
+            'description': 'md5:466a206abd21f3a6f776cdef290c23fb',
+            'timestamp': 1644901200,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'hls_prefer_native': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url_lang = 'fr' if '/l-episode?' in url else 'en'
+
+        content = self._download_json(
+            'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/episode/index.xml&crafterSite=cpacca&id=' + video_id,
+            video_id)
+        video_url = try_get(content, lambda x: x['page']['details']['videoUrl'], compat_str)
+        formats = []
+        if video_url:
+            content = content['page']
+            title = str_or_none(content['details']['title_%s_t' % (url_lang, )])
+            formats = self._extract_m3u8_formats(video_url, video_id, m3u8_id='hls', ext='mp4')
+            for fmt in formats:
+                # prefer language to match URL
+                fmt_lang = fmt.get('language')
+                if fmt_lang == url_lang:
+                    fmt['language_preference'] = 10
+                elif not fmt_lang:
+                    fmt['language_preference'] = -1
+                else:
+                    fmt['language_preference'] = -10
+
+        self._sort_formats(formats)
+
+        category = str_or_none(content['details']['category_%s_t' % (url_lang, )])
+
+        def is_live(v_type):
+            return (v_type == 'live') if v_type is not None else None
+
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title,
+            'description': str_or_none(content['details'].get('description_%s_t' % (url_lang, ))),
+            'timestamp': unified_timestamp(content['details'].get('liveDateTime')),
+            'category': [category] if category else None,
+            'thumbnail': urljoin(url, str_or_none(content['details'].get('image_%s_s' % (url_lang, )))),
+            'is_live': is_live(content['details'].get('type')),
+        }
+
+
+class CPACPlaylistIE(InfoExtractor):
+    IE_NAME = 'cpac:playlist'
+    _VALID_URL = r'(?i)https?://(?:www\.)?cpac\.ca/(?:program|search|(?P<fr>emission|rechercher))\?(?:[^&]+&)*?(?P<id>(?:id=\d+|programId=\d+|key=[^&]+))'
+
+    _TESTS = [{
+        'url': 'https://www.cpac.ca/program?id=6',
+        'info_dict': {
+            'id': 'id=6',
+            'title': 'Headline Politics',
+            'description': 'Watch CPAC’s signature long-form coverage of the day’s pressing political events as they unfold.',
+        },
+        'playlist_count': 10,
+    }, {
+        'url': 'https://www.cpac.ca/search?key=hudson&type=all&order=desc',
+        'info_dict': {
+            'id': 'key=hudson',
+            'title': 'hudson',
+        },
+        'playlist_count': 22,
+    }, {
+        'url': 'https://www.cpac.ca/search?programId=50',
+        'info_dict': {
+            'id': 'programId=50',
+            'title': '50',
+        },
+        'playlist_count': 9,
+    }, {
+        'url': 'https://www.cpac.ca/emission?id=6',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.cpac.ca/rechercher?key=hudson&type=all&order=desc',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url_lang = 'fr' if any(x in url for x in ('/emission?', '/rechercher?')) else 'en'
+        pl_type, list_type = ('program', 'itemList') if any(x in url for x in ('/program?', '/emission?')) else ('search', 'searchResult')
+        api_url = (
+            'https://www.cpac.ca/api/1/services/contentModel.json?url=/site/website/%s/index.xml&crafterSite=cpacca&%s'
+            % (pl_type, video_id, ))
+        content = self._download_json(api_url, video_id)
+        entries = []
+        total_pages = int_or_none(try_get(content, lambda x: x['page'][list_type]['totalPages']), default=1)
+        for page in range(1, total_pages + 1):
+            if page > 1:
+                api_url = update_url_query(api_url, {'page': '%d' % (page, ), })
+                content = self._download_json(
+                    api_url, video_id,
+                    note='Downloading continuation - %d' % (page, ),
+                    fatal=False)
+
+            for item in try_get(content, lambda x: x['page'][list_type]['item'], list) or []:
+                episode_url = urljoin(url, try_get(item, lambda x: x['url_%s_s' % (url_lang, )]))
+                if episode_url:
+                    entries.append(episode_url)
+
+        return self.playlist_result(
+            (self.url_result(entry) for entry in entries),
+            playlist_id=video_id,
+            playlist_title=try_get(content, lambda x: x['page']['program']['title_%s_t' % (url_lang, )]) or video_id.split('=')[-1],
+            playlist_description=try_get(content, lambda x: x['page']['program']['description_%s_t' % (url_lang, )]),
+        )

youtube_dl/extractor/extractors.py

@@ -51,6 +51,10 @@ from .anvato import AnvatoIE
 from .aol import AolIE
 from .allocine import AllocineIE
 from .aliexpress import AliExpressLiveIE
+from .alsace20tv import (
+    Alsace20TVIE,
+    Alsace20TVEmbedIE,
+)
 from .apa import APAIE
 from .aparat import AparatIE
 from .appleconnect import AppleConnectIE
@@ -115,6 +119,7 @@ from .bfmtv import (
 )
 from .bibeltv import BibelTVIE
 from .bigflix import BigflixIE
+from .bigo import BigoIE
 from .bild import BildIE
 from .bilibili import (
     BiliBiliIE,
@@ -254,6 +259,10 @@ from .commonprotocols import (
 from .condenast import CondeNastIE
 from .contv import CONtvIE
 from .corus import CorusIE
+from .cpac import (
+    CPACIE,
+    CPACPlaylistIE,
+)
 from .cracked import CrackedIE
 from .crackle import CrackleIE
 from .crooksandliars import CrooksAndLiarsIE

youtube_dl/extractor/myspass.py

@@ -35,7 +35,9 @@ class MySpassIE(InfoExtractor):
         title = xpath_text(metadata, 'title', fatal=True)
         video_url = xpath_text(metadata, 'url_flv', 'download url', True)
         video_id_int = int(video_id)
-        for group in re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url).groups():
+
+        grps = re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url)
+        for group in grps.groups() if grps else []:
             group_int = int(group)
             if group_int > video_id_int:
                 video_url = video_url.replace(