New upstream version 2019.01.16

[youtubedl] / youtube_dl / extractor / rutube.py

diff --git a/youtube_dl/extractor/rutube.py b/youtube_dl/extractor/rutube.py
index 6b09550b01d19b76484adb3301ec2a56156b5b1f..10ac8ed1f22ad943dc210430d0363d9a4aa0b483 100644 (file)
--- a/youtube_dl/extractor/rutube.py
+++ b/youtube_dl/extractor/rutube.py
@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re


@@ -7,63 +7,114 @@ import itertools
 from .common import InfoExtractor
 from ..compat import (
     compat_str,
 from .common import InfoExtractor
 from ..compat import (
     compat_str,

+    compat_parse_qs,
+    compat_urllib_parse_urlparse,

 )
 from ..utils import (
     determine_ext,
 )
 from ..utils import (
     determine_ext,

-    unified_strdate,
+    bool_or_none,
+    int_or_none,
+    try_get,
+    unified_timestamp,
+    url_or_none,

 )
 
 
 )
 
 

-class RutubeIE(InfoExtractor):
+class RutubeBaseIE(InfoExtractor):
+    def _extract_video(self, video, video_id=None, require_title=True):
+        title = video['title'] if require_title else video.get('title')
+
+        age_limit = video.get('is_adult')
+        if age_limit is not None:
+            age_limit = 18 if age_limit is True else 0
+
+        uploader_id = try_get(video, lambda x: x['author']['id'])
+        category = try_get(video, lambda x: x['category']['name'])
+
+        return {
+            'id': video.get('id') or video_id,
+            'title': title,
+            'description': video.get('description'),
+            'thumbnail': video.get('thumbnail_url'),
+            'duration': int_or_none(video.get('duration')),
+            'uploader': try_get(video, lambda x: x['author']['name']),
+            'uploader_id': compat_str(uploader_id) if uploader_id else None,
+            'timestamp': unified_timestamp(video.get('created_ts')),
+            'category': [category] if category else None,
+            'age_limit': age_limit,
+            'view_count': int_or_none(video.get('hits')),
+            'comment_count': int_or_none(video.get('comments_count')),
+            'is_live': bool_or_none(video.get('is_livestream')),
+        }
+
+
+class RutubeIE(RutubeBaseIE):

     IE_NAME = 'rutube'
     IE_DESC = 'Rutube videos'
     IE_NAME = 'rutube'
     IE_DESC = 'Rutube videos'

-    _VALID_URL = r'https?://rutube\.ru/video/(?P<id>[\da-z]{32})'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/(?P<id>[\da-z]{32})'

 
 

-    _TEST = {
+    _TESTS = [{

         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',
         'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/',

+        'md5': '79938ade01294ef7e27574890d0d3769',

         'info_dict': {
             'id': '3eac3b4561676c17df9132a9a1e62e3e',
         'info_dict': {
             'id': '3eac3b4561676c17df9132a9a1e62e3e',

-            'ext': 'mp4',
+            'ext': 'flv',

             'title': 'Раненный кенгуру забежал в аптеку',
             'description': 'http://www.ntdtv.ru ',
             'duration': 80,
             'uploader': 'NTDRussian',
             'uploader_id': '29790',
             'title': 'Раненный кенгуру забежал в аптеку',
             'description': 'http://www.ntdtv.ru ',
             'duration': 80,
             'uploader': 'NTDRussian',
             'uploader_id': '29790',

+            'timestamp': 1381943602,

             'upload_date': '20131016',
             'age_limit': 0,
         },
             'upload_date': '20131016',
             'age_limit': 0,
         },

-        'params': {
-            # It requires ffmpeg (m3u8 download)
-            'skip_download': True,
-        },
-    }
+    }, {
+        'url': 'http://rutube.ru/play/embed/a10e53b86e8f349080f718582ce4c661',
+        'only_matching': True,
+    }, {
+        'url': 'http://rutube.ru/embed/a10e53b86e8f349080f718582ce4c661',
+        'only_matching': True,
+    }, {
+        'url': 'http://rutube.ru/video/3eac3b4561676c17df9132a9a1e62e3e/?pl_id=4252',
+        'only_matching': True,
+    }, {
+        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_type=source',
+        'only_matching': True,
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if RutubePlaylistIE.suitable(url) else super(RutubeIE, cls).suitable(url)
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return [mobj.group('url') for mobj in re.finditer(
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//rutube\.ru/embed/[\da-z]{32}.*?)\1',
+            webpage)]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)

+

         video = self._download_json(
             'http://rutube.ru/api/video/%s/?format=json' % video_id,
             video_id, 'Downloading video JSON')
 
         video = self._download_json(
             'http://rutube.ru/api/video/%s/?format=json' % video_id,
             video_id, 'Downloading video JSON')
 

-        # Some videos don't have the author field
-        author = video.get('author') or {}
+        info = self._extract_video(video, video_id)

 
         options = self._download_json(
             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,
 
         options = self._download_json(
             'http://rutube.ru/api/play/options/%s/?format=json' % video_id,

-            video_id, 'Downloading options JSON')
+            video_id, 'Downloading options JSON',
+            headers=self.geo_verification_headers())

 
         formats = []
         for format_id, format_url in options['video_balancer'].items():
             ext = determine_ext(format_url)
             if ext == 'm3u8':
 
         formats = []
         for format_id, format_url in options['video_balancer'].items():
             ext = determine_ext(format_url)
             if ext == 'm3u8':

-                m3u8_formats = self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False)
-                if m3u8_formats:
-                    formats.extend(m3u8_formats)
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', m3u8_id=format_id, fatal=False))

             elif ext == 'f4m':
             elif ext == 'f4m':

-                f4m_formats = self._extract_f4m_formats(
-                    format_url, video_id, f4m_id=format_id, fatal=False)
-                if f4m_formats:
-                    formats.extend(f4m_formats)
+                formats.extend(self._extract_f4m_formats(
+                    format_url, video_id, f4m_id=format_id, fatal=False))

             else:
                 formats.append({
                     'url': format_url,
             else:
                 formats.append({
                     'url': format_url,


@@ -71,31 +122,21 @@ class RutubeIE(InfoExtractor):
                 })
         self._sort_formats(formats)
 
                 })
         self._sort_formats(formats)
 

-        return {
-            'id': video['id'],
-            'title': video['title'],
-            'description': video['description'],
-            'duration': video['duration'],
-            'view_count': video['hits'],
-            'formats': formats,
-            'thumbnail': video['thumbnail_url'],
-            'uploader': author.get('name'),
-            'uploader_id': compat_str(author['id']) if author else None,
-            'upload_date': unified_strdate(video['created_ts']),
-            'age_limit': 18 if video['is_adult'] else 0,
-        }
+        info['formats'] = formats
+        return info

 
 
 class RutubeEmbedIE(InfoExtractor):
     IE_NAME = 'rutube:embed'
     IE_DESC = 'Rutube embedded videos'
 
 
 class RutubeEmbedIE(InfoExtractor):
     IE_NAME = 'rutube:embed'
     IE_DESC = 'Rutube embedded videos'

-    _VALID_URL = 'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|play)/embed/(?P<id>[0-9]+)'

 
     _TESTS = [{
         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',
 
     _TESTS = [{
         'url': 'http://rutube.ru/video/embed/6722881?vk_puid37=&vk_puid38=',
         'info_dict': {
             'id': 'a10e53b86e8f349080f718582ce4c661',

-            'ext': 'mp4',
+            'ext': 'flv',
+            'timestamp': 1387830582,

             'upload_date': '20131223',
             'uploader_id': '297833',
             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',
             'upload_date': '20131223',
             'uploader_id': '297833',
             'description': 'Видео группы ★http://vk.com/foxkidsreset★ музей Fox Kids и Jetix<br/><br/> восстановлено и сделано в шикоформате subziro89 http://vk.com/subziro89',


@@ -103,7 +144,7 @@ class RutubeEmbedIE(InfoExtractor):
             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
         },
         'params': {
             'title': 'Мистический городок Эйри в Индиан 5 серия озвучка subziro89',
         },
         'params': {

-            'skip_download': 'Requires ffmpeg',
+            'skip_download': True,

         },
     }, {
         'url': 'http://rutube.ru/play/embed/8083783',
         },
     }, {
         'url': 'http://rutube.ru/play/embed/8083783',


@@ -117,13 +158,54 @@ class RutubeEmbedIE(InfoExtractor):
         canonical_url = self._html_search_regex(
             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
             'Canonical URL')
         canonical_url = self._html_search_regex(
             r'<link\s+rel="canonical"\s+href="([^"]+?)"', webpage,
             'Canonical URL')

-        return self.url_result(canonical_url, 'Rutube')
+        return self.url_result(canonical_url, RutubeIE.ie_key())
+
+
+class RutubePlaylistBaseIE(RutubeBaseIE):
+    def _next_page_url(self, page_num, playlist_id, *args, **kwargs):
+        return self._PAGE_TEMPLATE % (playlist_id, page_num)
+
+    def _entries(self, playlist_id, *args, **kwargs):
+        next_page_url = None
+        for pagenum in itertools.count(1):
+            page = self._download_json(
+                next_page_url or self._next_page_url(
+                    pagenum, playlist_id, *args, **kwargs),
+                playlist_id, 'Downloading page %s' % pagenum)
+
+            results = page.get('results')
+            if not results or not isinstance(results, list):
+                break
+
+            for result in results:
+                video_url = url_or_none(result.get('video_url'))
+                if not video_url:
+                    continue
+                entry = self._extract_video(result, require_title=False)
+                entry.update({
+                    '_type': 'url',
+                    'url': video_url,
+                    'ie_key': RutubeIE.ie_key(),
+                })
+                yield entry
+
+            next_page_url = page.get('next')
+            if not next_page_url or not page.get('has_next'):
+                break

 
 

+    def _extract_playlist(self, playlist_id, *args, **kwargs):
+        return self.playlist_result(
+            self._entries(playlist_id, *args, **kwargs),
+            playlist_id, kwargs.get('playlist_name'))

 
 

-class RutubeChannelIE(InfoExtractor):
+    def _real_extract(self, url):
+        return self._extract_playlist(self._match_id(url))
+
+
+class RutubeChannelIE(RutubePlaylistBaseIE):

     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'
     IE_NAME = 'rutube:channel'
     IE_DESC = 'Rutube channels'

-    _VALID_URL = r'http://rutube\.ru/tags/video/(?P<id>\d+)'
+    _VALID_URL = r'https?://rutube\.ru/tags/video/(?P<id>\d+)'

     _TESTS = [{
         'url': 'http://rutube.ru/tags/video/1800/',
         'info_dict': {
     _TESTS = [{
         'url': 'http://rutube.ru/tags/video/1800/',
         'info_dict': {


@@ -134,30 +216,11 @@ class RutubeChannelIE(InfoExtractor):
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/tags/video/%s/?page=%s&format=json'
 

-    def _extract_videos(self, channel_id, channel_title=None):
-        entries = []
-        for pagenum in itertools.count(1):
-            page = self._download_json(
-                self._PAGE_TEMPLATE % (channel_id, pagenum),
-                channel_id, 'Downloading page %s' % pagenum)
-            results = page['results']
-            if not results:
-                break
-            entries.extend(self.url_result(result['video_url'], 'Rutube') for result in results)
-            if not page['has_next']:
-                break
-        return self.playlist_result(entries, channel_id, channel_title)
-
-    def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        channel_id = mobj.group('id')
-        return self._extract_videos(channel_id)
-

 
 

-class RutubeMovieIE(RutubeChannelIE):
+class RutubeMovieIE(RutubePlaylistBaseIE):

     IE_NAME = 'rutube:movie'
     IE_DESC = 'Rutube movies'
     IE_NAME = 'rutube:movie'
     IE_DESC = 'Rutube movies'

-    _VALID_URL = r'http://rutube\.ru/metainfo/tv/(?P<id>\d+)'
+    _VALID_URL = r'https?://rutube\.ru/metainfo/tv/(?P<id>\d+)'

     _TESTS = []
 
     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'
     _TESTS = []
 
     _MOVIE_TEMPLATE = 'http://rutube.ru/api/metainfo/tv/%s/?format=json'


@@ -168,14 +231,14 @@ class RutubeMovieIE(RutubeChannelIE):
         movie = self._download_json(
             self._MOVIE_TEMPLATE % movie_id, movie_id,
             'Downloading movie JSON')
         movie = self._download_json(
             self._MOVIE_TEMPLATE % movie_id, movie_id,
             'Downloading movie JSON')

-        movie_name = movie['name']
-        return self._extract_videos(movie_id, movie_name)
+        return self._extract_playlist(
+            movie_id, playlist_name=movie.get('name'))

 
 
 
 

-class RutubePersonIE(RutubeChannelIE):
+class RutubePersonIE(RutubePlaylistBaseIE):

     IE_NAME = 'rutube:person'
     IE_DESC = 'Rutube person videos'
     IE_NAME = 'rutube:person'
     IE_DESC = 'Rutube person videos'

-    _VALID_URL = r'http://rutube\.ru/video/person/(?P<id>\d+)'
+    _VALID_URL = r'https?://rutube\.ru/video/person/(?P<id>\d+)'

     _TESTS = [{
         'url': 'http://rutube.ru/video/person/313878/',
         'info_dict': {
     _TESTS = [{
         'url': 'http://rutube.ru/video/person/313878/',
         'info_dict': {


@@ -185,3 +248,37 @@ class RutubePersonIE(RutubeChannelIE):
     }]
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'
     }]
 
     _PAGE_TEMPLATE = 'http://rutube.ru/api/video/person/%s/?page=%s&format=json'

+
+
+class RutubePlaylistIE(RutubePlaylistBaseIE):
+    IE_NAME = 'rutube:playlist'
+    IE_DESC = 'Rutube playlists'
+    _VALID_URL = r'https?://rutube\.ru/(?:video|(?:play/)?embed)/[\da-z]{32}/\?.*?\bpl_id=(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://rutube.ru/video/cecd58ed7d531fc0f3d795d51cee9026/?pl_id=3097&pl_type=tag',
+        'info_dict': {
+            'id': '3097',
+        },
+        'playlist_count': 27,
+    }, {
+        'url': 'https://rutube.ru/video/10b3a03fc01d5bbcc632a2f3514e8aab/?pl_id=4252&pl_type=source',
+        'only_matching': True,
+    }]
+
+    _PAGE_TEMPLATE = 'http://rutube.ru/api/playlist/%s/%s/?page=%s&format=json'
+
+    @classmethod
+    def suitable(cls, url):
+        if not super(RutubePlaylistIE, cls).suitable(url):
+            return False
+        params = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        return params.get('pl_type', [None])[0] and int_or_none(params.get('pl_id', [None])[0])
+
+    def _next_page_url(self, page_num, playlist_id, item_kind):
+        return self._PAGE_TEMPLATE % (item_kind, playlist_id, page_num)
+
+    def _real_extract(self, url):
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        playlist_kind = qs['pl_type'][0]
+        playlist_id = qs['pl_id'][0]
+        return self._extract_playlist(playlist_id, item_kind=playlist_kind)