]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/odnoklassniki.py
Rapsys Git / youtubedl / blobdiff
? search:
summary | shortlog | log | commit | commitdiff | tree
raw | inline | side by side
Update upstream source from tag 'upstream/2020.07.28'
[youtubedl] / youtube_dl / extractor / odnoklassniki.py
diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py
index f9e064a60e445668200b759ca4e0ad1a6f7c28ab..7ed9fac5510f5f69b9eb23c07163bd50f91fdca9 100644 (file)
--- a/youtube_dl/extractor/odnoklassniki.py
+++ b/youtube_dl/extractor/odnoklassniki.py
@@ -1,23 +1,42 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from .common import InfoExtractor
-from ..compat import compat_urllib_parse_unquote
+from ..compat import (
+    compat_etree_fromstring,
+    compat_parse_qs,
+    compat_urllib_parse_unquote,
+    compat_urllib_parse_urlparse,
+)
 from ..utils import (
     ExtractorError,
     unified_strdate,
     int_or_none,
     qualities,
     unescapeHTML,
 from ..utils import (
     ExtractorError,
     unified_strdate,
     int_or_none,
     qualities,
     unescapeHTML,
+    urlencode_postdata,
 )
 
 
 class OdnoklassnikiIE(InfoExtractor):
 )
 
 
 class OdnoklassnikiIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|m|mobile)\.)?(?:odnoklassniki|ok)\.ru/(?:video(?:embed)?|web-api/video/moviePlayer)/(?P<id>[\d-]+)'
+    _VALID_URL = r'''(?x)
+                https?://
+                    (?:(?:www|m|mobile)\.)?
+                    (?:odnoklassniki|ok)\.ru/
+                    (?:
+                        video(?:embed)?/|
+                        web-api/video/moviePlayer/|
+                        live/|
+                        dk\?.*?st\.mvId=
+                    )
+                    (?P<id>[\d-]+)
+                '''
     _TESTS = [{
         # metadata in JSON
         'url': 'http://ok.ru/video/20079905452',
     _TESTS = [{
         # metadata in JSON
         'url': 'http://ok.ru/video/20079905452',
-        'md5': '6ba728d85d60aa2e6dd37c9e70fdc6bc',
+        'md5': '0b62089b479e06681abaaca9d204f152',
         'info_dict': {
             'id': '20079905452',
             'ext': 'mp4',
         'info_dict': {
             'id': '20079905452',
             'ext': 'mp4',
@@ -29,11 +48,10 @@ class OdnoklassnikiIE(InfoExtractor):
             'like_count': int,
             'age_limit': 0,
         },
             'like_count': int,
             'age_limit': 0,
         },
-        'skip': 'Video has been blocked',
     }, {
         # metadataUrl
     }, {
         # metadataUrl
-        'url': 'http://ok.ru/video/63567059965189-0',
-        'md5': '9676cf86eff5391d35dea675d224e131',
+        'url': 'http://ok.ru/video/63567059965189-0?fromTime=5',
+        'md5': '6ff470ea2dd51d5d18c295a355b0b6bc',
         'info_dict': {
             'id': '63567059965189-0',
             'ext': 'mp4',
         'info_dict': {
             'id': '63567059965189-0',
             'ext': 'mp4',
@@ -44,22 +62,40 @@ class OdnoklassnikiIE(InfoExtractor):
             'uploader': '☭ Андрей Мещанинов ☭',
             'like_count': int,
             'age_limit': 0,
             'uploader': '☭ Андрей Мещанинов ☭',
             'like_count': int,
             'age_limit': 0,
+            'start_time': 5,
         },
     }, {
         # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
         'url': 'http://ok.ru/video/64211978996595-1',
         },
     }, {
         # YouTube embed (metadataUrl, provider == USER_YOUTUBE)
         'url': 'http://ok.ru/video/64211978996595-1',
-        'md5': '5d7475d428845cd2e13bae6f1a992278',
+        'md5': '2f206894ffb5dbfcce2c5a14b909eea5',
         'info_dict': {
         'info_dict': {
-            'id': '64211978996595-1',
+            'id': 'V_VztHT5BzY',
             'ext': 'mp4',
             'title': 'Космическая среда от 26 августа 2015',
             'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
             'duration': 440,
             'upload_date': '20150826',
             'ext': 'mp4',
             'title': 'Космическая среда от 26 августа 2015',
             'description': 'md5:848eb8b85e5e3471a3a803dae1343ed0',
             'duration': 440,
             'upload_date': '20150826',
-            'uploader_id': '750099571',
-            'uploader': 'Ð\90лина Ð\9f',
+            'uploader_id': 'tvroscosmos',
+            'uploader': 'ТелеÑ\81Ñ\82Ñ\83диÑ\8f Ð Ð¾Ñ\81коÑ\81моÑ\81а',
             'age_limit': 0,
         },
             'age_limit': 0,
         },
+    }, {
+        # YouTube embed (metadata, provider == USER_YOUTUBE, no metadata.movie.title field)
+        'url': 'http://ok.ru/video/62036049272859-0',
+        'info_dict': {
+            'id': '62036049272859-0',
+            'ext': 'mp4',
+            'title': 'МУЗЫКА     ДОЖДЯ .',
+            'description': 'md5:6f1867132bd96e33bf53eda1091e8ed0',
+            'upload_date': '20120106',
+            'uploader_id': '473534735899',
+            'uploader': 'МARINA D',
+            'age_limit': 0,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'skip': 'Video has not been found',
     }, {
         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
         'only_matching': True,
     }, {
         'url': 'http://ok.ru/web-api/video/moviePlayer/20079905452',
         'only_matching': True,
@@ -75,9 +111,29 @@ class OdnoklassnikiIE(InfoExtractor):
     }, {
         'url': 'http://mobile.ok.ru/video/20079905452',
         'only_matching': True,
     }, {
         'url': 'http://mobile.ok.ru/video/20079905452',
         'only_matching': True,
+    }, {
+        'url': 'https://www.ok.ru/live/484531969818',
+        'only_matching': True,
+    }, {
+        'url': 'https://m.ok.ru/dk?st.cmd=movieLayer&st.discId=863789452017&st.retLoc=friend&st.rtu=%2Fdk%3Fst.cmd%3DfriendMovies%26st.mode%3Down%26st.mrkId%3D%257B%2522uploadedMovieMarker%2522%253A%257B%2522marker%2522%253A%25221519410114503%2522%252C%2522hasMore%2522%253Atrue%257D%252C%2522sharedMovieMarker%2522%253A%257B%2522marker%2522%253Anull%252C%2522hasMore%2522%253Afalse%257D%257D%26st.friendId%3D561722190321%26st.frwd%3Don%26_prevCmd%3DfriendMovies%26tkn%3D7257&st.discType=MOVIE&st.mvId=863789452017&_prevCmd=friendMovies&tkn=3648#lst#',
+        'only_matching': True,
+    }, {
+        # Paid video
+        'url': 'https://ok.ru/video/954886983203',
+        'only_matching': True,
     }]
 
     }]
 
+    @staticmethod
+    def _extract_url(webpage):
+        mobj = re.search(
+            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
+        if mobj:
+            return mobj.group('url')
+
     def _real_extract(self, url):
     def _real_extract(self, url):
+        start_time = int_or_none(compat_parse_qs(
+            compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0])
+
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(
@@ -101,12 +157,24 @@ class OdnoklassnikiIE(InfoExtractor):
         if metadata:
             metadata = self._parse_json(metadata, video_id)
         else:
         if metadata:
             metadata = self._parse_json(metadata, video_id)
         else:
+            data = {}
+            st_location = flashvars.get('location')
+            if st_location:
+                data['st.location'] = st_location
             metadata = self._download_json(
                 compat_urllib_parse_unquote(flashvars['metadataUrl']),
             metadata = self._download_json(
                 compat_urllib_parse_unquote(flashvars['metadataUrl']),
-                video_id, 'Downloading metadata JSON')
+                video_id, 'Downloading metadata JSON',
+                data=urlencode_postdata(data))
 
         movie = metadata['movie']
 
         movie = metadata['movie']
-        title = movie['title']
+
+        # Some embedded videos may not contain title in movie dict (e.g.
+        # http://ok.ru/video/62036049272859-0) thus we allow missing title
+        # here and it's going to be extracted later by an extractor that
+        # will process the actual embed.
+        provider = metadata.get('provider')
+        title = movie['title'] if provider == 'UPLOADED_ODKL' else movie.get('title')
+
         thumbnail = movie.get('poster')
         duration = int_or_none(movie.get('duration'))
 
         thumbnail = movie.get('poster')
         duration = int_or_none(movie.get('duration'))
 
@@ -135,23 +203,65 @@ class OdnoklassnikiIE(InfoExtractor):
             'uploader_id': uploader_id,
             'like_count': like_count,
             'age_limit': age_limit,
             'uploader_id': uploader_id,
             'like_count': like_count,
             'age_limit': age_limit,
+            'start_time': start_time,
         }
 
         }
 
-        if metadata.get('provider') == 'USER_YOUTUBE':
+        if provider == 'USER_YOUTUBE':
             info.update({
                 '_type': 'url_transparent',
                 'url': movie['contentId'],
             })
             return info
 
             info.update({
                 '_type': 'url_transparent',
                 'url': movie['contentId'],
             })
             return info
 
-        quality = qualities(('mobile', 'lowest', 'low', 'sd', 'hd'))
+        assert title
+        if provider == 'LIVE_TV_APP':
+            info['title'] = self._live_title(title)
+
+        quality = qualities(('4', '0', '1', '2', '3', '5'))
 
         formats = [{
             'url': f['url'],
             'ext': 'mp4',
             'format_id': f['name'],
 
         formats = [{
             'url': f['url'],
             'ext': 'mp4',
             'format_id': f['name'],
-            'quality': quality(f['name']),
         } for f in metadata['videos']]
         } for f in metadata['videos']]
+
+        m3u8_url = metadata.get('hlsManifestUrl')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', 'm3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        dash_manifest = metadata.get('metadataEmbedded')
+        if dash_manifest:
+            formats.extend(self._parse_mpd_formats(
+                compat_etree_fromstring(dash_manifest), 'mpd'))
+
+        for fmt in formats:
+            fmt_type = self._search_regex(
+                r'\btype[/=](\d)', fmt['url'],
+                'format type', default=None)
+            if fmt_type:
+                fmt['quality'] = quality(fmt_type)
+
+        # Live formats
+        m3u8_url = metadata.get('hlsMasterPlaylistUrl')
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, video_id, 'mp4', entry_protocol='m3u8',
+                m3u8_id='hls', fatal=False))
+        rtmp_url = metadata.get('rtmpUrl')
+        if rtmp_url:
+            formats.append({
+                'url': rtmp_url,
+                'format_id': 'rtmp',
+                'ext': 'flv',
+            })
+
+        if not formats:
+            payment_info = metadata.get('paymentInfo')
+            if payment_info:
+                raise ExtractorError('This video is paid, subscribe to download it', expected=True)
+
         self._sort_formats(formats)
 
         info['formats'] = formats
         self._sort_formats(formats)
 
         info['formats'] = formats
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...