debian/control: Mark my GitHub trees as the preferred repos.

[youtubedl] / youtube_dl / extractor / vk.py

diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py
index 7c42a4f54864eeb370c6a4583daae950262b45b8..8b6dc0e244982f46cbc0d65bf5133b3505779fb0 100644 (file)
--- a/youtube_dl/extractor/vk.py
+++ b/youtube_dl/extractor/vk.py
@@ -3,13 +3,9 @@ from __future__ import unicode_literals
 
 import collections
 import re
 
 import collections
 import re

-import sys

 
 from .common import InfoExtractor
 
 from .common import InfoExtractor

-from ..compat import (
-    compat_str,
-    compat_urlparse,
-)
+from ..compat import compat_urlparse

 from ..utils import (
     clean_html,
     ExtractorError,
 from ..utils import (
     clean_html,
     ExtractorError,


@@ -17,21 +13,24 @@ from ..utils import (
     int_or_none,
     orderedSet,
     remove_start,
     int_or_none,
     orderedSet,
     remove_start,

+    str_or_none,

     str_to_int,
     unescapeHTML,
     unified_timestamp,
     str_to_int,
     unescapeHTML,
     unified_timestamp,

+    url_or_none,

     urlencode_postdata,
 )
 from .dailymotion import DailymotionIE
 from .pladform import PladformIE
 from .vimeo import VimeoIE
     urlencode_postdata,
 )
 from .dailymotion import DailymotionIE
 from .pladform import PladformIE
 from .vimeo import VimeoIE

+from .youtube import YoutubeIE

 
 
 class VKBaseIE(InfoExtractor):
     _NETRC_MACHINE = 'vk'
 
     def _login(self):
 
 
 class VKBaseIE(InfoExtractor):
     _NETRC_MACHINE = 'vk'
 
     def _login(self):

-        (username, password) = self._get_login_info()
+        username, password = self._get_login_info()

         if username is None:
             return
 
         if username is None:
             return
 


@@ -45,28 +44,13 @@ class VKBaseIE(InfoExtractor):
             'pass': password.encode('cp1251'),
         })
 
             'pass': password.encode('cp1251'),
         })
 

-        # https://new.vk.com/ serves two same remixlhk cookies in Set-Cookie header
-        # and expects the first one to be set rather than second (see
-        # https://github.com/rg3/youtube-dl/issues/9841#issuecomment-227871201).
-        # As of RFC6265 the newer one cookie should be set into cookie store
-        # what actually happens.
-        # We will workaround this VK issue by resetting the remixlhk cookie to
-        # the first one manually.
-        for header, cookies in url_handle.headers.items():
-            if header.lower() != 'set-cookie':
-                continue
-            if sys.version_info[0] >= 3:
-                cookies = cookies.encode('iso-8859-1')
-            cookies = cookies.decode('utf-8')
-            remixlhk = re.search(r'remixlhk=(.+?);.*?\bdomain=(.+?)(?:[,;]|$)', cookies)
-            if remixlhk:
-                value, domain = remixlhk.groups()
-                self._set_cookie(domain, 'remixlhk', value)
-                break
+        # vk serves two same remixlhk cookies in Set-Cookie header and expects
+        # first one to be actually set
+        self._apply_first_set_cookie_header(url_handle, 'remixlhk')

 
         login_page = self._download_webpage(
             'https://login.vk.com/?act=login', None,
 
         login_page = self._download_webpage(
             'https://login.vk.com/?act=login', None,

-            note='Logging in as %s' % username,
+            note='Logging in',

             data=urlencode_postdata(login_form))
 
         if re.search(r'onLoginFailed', login_page):
             data=urlencode_postdata(login_form))
 
         if re.search(r'onLoginFailed', login_page):


@@ -98,30 +82,30 @@ class VKIE(VKBaseIE):
     _TESTS = [
         {
             'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',
     _TESTS = [
         {
             'url': 'http://vk.com/videos-77521?z=video-77521_162222515%2Fclub77521',

-            'md5': '0deae91935c54e00003c2a00646315f0',
+            'md5': '7babad3b85ea2e91948005b1b8b0cb84',

             'info_dict': {
             'info_dict': {

-                'id': '162222515',
-                'ext': 'flv',
+                'id': '-77521_162222515',
+                'ext': 'mp4',

                 'title': 'ProtivoGunz - Хуёвая песня',
                 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',
                 'title': 'ProtivoGunz - Хуёвая песня',
                 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*',

+                'uploader_id': '-77521',

                 'duration': 195,
                 'duration': 195,

-                'timestamp': 1329060660,
+                'timestamp': 1329049880,

                 'upload_date': '20120212',
                 'upload_date': '20120212',

-                'view_count': int,

             },
         },
         {
             'url': 'http://vk.com/video205387401_165548505',
             'md5': '6c0aeb2e90396ba97035b9cbde548700',
             'info_dict': {
             },
         },
         {
             'url': 'http://vk.com/video205387401_165548505',
             'md5': '6c0aeb2e90396ba97035b9cbde548700',
             'info_dict': {

-                'id': '165548505',
+                'id': '205387401_165548505',

                 'ext': 'mp4',
                 'ext': 'mp4',

-                'uploader': 'Tom Cruise',

                 'title': 'No name',
                 'title': 'No name',

+                'uploader': 'Tom Cruise',
+                'uploader_id': '205387401',

                 'duration': 9,
                 'duration': 9,

-                'timestamp': 1374374880,
-                'upload_date': '20130721',
-                'view_count': int,
+                'timestamp': 1374364108,
+                'upload_date': '20130720',

             }
         },
         {
             }
         },
         {


@@ -129,7 +113,7 @@ class VKIE(VKBaseIE):
             'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
             'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
             'info_dict': {
             'url': 'http://vk.com/video_ext.php?oid=32194266&id=162925554&hash=7d8c2e0d5e05aeaa&hd=1',
             'md5': 'c7ce8f1f87bec05b3de07fdeafe21a0a',
             'info_dict': {

-                'id': '162925554',
+                'id': '32194266_162925554',

                 'ext': 'mp4',
                 'uploader': 'Vladimir Gavrin',
                 'title': 'Lin Dan',
                 'ext': 'mp4',
                 'uploader': 'Vladimir Gavrin',
                 'title': 'Lin Dan',


@@ -146,7 +130,7 @@ class VKIE(VKBaseIE):
             'md5': 'a590bcaf3d543576c9bd162812387666',
             'note': 'Only available for registered users',
             'info_dict': {
             'md5': 'a590bcaf3d543576c9bd162812387666',
             'note': 'Only available for registered users',
             'info_dict': {

-                'id': '164049491',
+                'id': '-8871596_164049491',

                 'ext': 'mp4',
                 'uploader': 'Триллеры',
                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',
                 'ext': 'mp4',
                 'uploader': 'Триллеры',
                 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]',


@@ -160,7 +144,7 @@ class VKIE(VKBaseIE):
             'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
             'md5': '4d7a5ef8cf114dfa09577e57b2993202',
             'info_dict': {
             'url': 'http://vk.com/hd_kino_mania?z=video-43215063_168067957%2F15c66b9b533119788d',
             'md5': '4d7a5ef8cf114dfa09577e57b2993202',
             'info_dict': {

-                'id': '168067957',
+                'id': '-43215063_168067957',

                 'ext': 'mp4',
                 'uploader': 'Киномания - лучшее из мира кино',
                 'title': ' ',
                 'ext': 'mp4',
                 'uploader': 'Киномания - лучшее из мира кино',
                 'title': ' ',


@@ -174,7 +158,7 @@ class VKIE(VKBaseIE):
             'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
             'note': 'ivi.ru embed',
             'info_dict': {
             'md5': '0c45586baa71b7cb1d0784ee3f4e00a6',
             'note': 'ivi.ru embed',
             'info_dict': {

-                'id': '60690',
+                'id': '-43215063_169084319',

                 'ext': 'mp4',
                 'title': 'Книга Илая',
                 'duration': 6771,
                 'ext': 'mp4',
                 'title': 'Книга Илая',
                 'duration': 6771,


@@ -188,7 +172,7 @@ class VKIE(VKBaseIE):
             'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
             'md5': '091287af5402239a1051c37ec7b92913',
             'info_dict': {
             'url': 'https://vk.com/video30481095_171201961?list=8764ae2d21f14088d4',
             'md5': '091287af5402239a1051c37ec7b92913',
             'info_dict': {

-                'id': '171201961',
+                'id': '30481095_171201961',

                 'ext': 'mp4',
                 'title': 'ТюменцевВВ_09.07.2015',
                 'uploader': 'Anton Ivanov',
                 'ext': 'mp4',
                 'title': 'ТюменцевВВ_09.07.2015',
                 'uploader': 'Anton Ivanov',


@@ -203,12 +187,12 @@ class VKIE(VKBaseIE):
             'url': 'https://vk.com/video276849682_170681728',
             'info_dict': {
                 'id': 'V3K4mi0SYkc',
             'url': 'https://vk.com/video276849682_170681728',
             'info_dict': {
                 'id': 'V3K4mi0SYkc',

-                'ext': 'webm',
+                'ext': 'mp4',

                 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",
                 'title': "DSWD Awards 'Children's Joy Foundation, Inc.' Certificate of Registration and License to Operate",

-                'description': 'md5:d9903938abdc74c738af77f527ca0596',
+                'description': 'md5:bf9c26cfa4acdfb146362682edd3827a',

                 'duration': 178,
                 'upload_date': '20130116',
                 'duration': 178,
                 'upload_date': '20130116',

-                'uploader': "Children's Joy Foundation",
+                'uploader': "Children's Joy Foundation Inc.",

                 'uploader_id': 'thecjf',
                 'view_count': int,
             },
                 'uploader_id': 'thecjf',
                 'view_count': int,
             },


@@ -220,6 +204,7 @@ class VKIE(VKBaseIE):
                 'id': 'k3lz2cmXyRuJQSjGHUv',
                 'ext': 'mp4',
                 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',
                 'id': 'k3lz2cmXyRuJQSjGHUv',
                 'ext': 'mp4',
                 'title': 'md5:d52606645c20b0ddbb21655adaa4f56f',

+                # TODO: fix test by fixing dailymotion description extraction

                 'description': 'md5:c651358f03c56f1150b555c26d90a0fd',
                 'uploader': 'AniLibria.Tv',
                 'upload_date': '20160914',
                 'description': 'md5:c651358f03c56f1150b555c26d90a0fd',
                 'uploader': 'AniLibria.Tv',
                 'upload_date': '20160914',


@@ -235,26 +220,32 @@ class VKIE(VKBaseIE):
             'url': 'http://vk.com/video-110305615_171782105',
             'md5': 'e13fcda136f99764872e739d13fac1d1',
             'info_dict': {
             'url': 'http://vk.com/video-110305615_171782105',
             'md5': 'e13fcda136f99764872e739d13fac1d1',
             'info_dict': {

-                'id': '171782105',
+                'id': '-110305615_171782105',

                 'ext': 'mp4',
                 'title': 'S-Dance, репетиции к The way show',
                 'uploader': 'THE WAY SHOW | 17 апреля',
                 'ext': 'mp4',
                 'title': 'S-Dance, репетиции к The way show',
                 'uploader': 'THE WAY SHOW | 17 апреля',

-                'timestamp': 1454870100,
+                'uploader_id': '-110305615',
+                'timestamp': 1454859345,

                 'upload_date': '20160207',
                 'upload_date': '20160207',

-                'view_count': int,
+            },
+            'params': {
+                'skip_download': True,

             },
         },
         {
             # finished live stream, postlive_mp4
             'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',
             },
         },
         {
             # finished live stream, postlive_mp4
             'url': 'https://vk.com/videos-387766?z=video-387766_456242764%2Fpl_-387766_-2',

-            'md5': '90d22d051fccbbe9becfccc615be6791',

             'info_dict': {
             'info_dict': {

-                'id': '456242764',
+                'id': '-387766_456242764',

                 'ext': 'mp4',
                 'ext': 'mp4',

-                'title': 'ИгроМир 2016 — день 1',
+                'title': 'ИгроМир 2016 День 1 — Игромания Утром',

                 'uploader': 'Игромания',
                 'duration': 5239,
                 'uploader': 'Игромания',
                 'duration': 5239,

-                'view_count': int,
+                # TODO: use act=show to extract view_count
+                # 'view_count': int,
+                'upload_date': '20160929',
+                'uploader_id': '-387766',
+                'timestamp': 1475137527,

             },
         },
         {
             },
         },
         {


@@ -286,15 +277,19 @@ class VKIE(VKBaseIE):
             # This video is no longer available, because its author has been blocked.
             'url': 'https://vk.com/video-10639516_456240611',
             'only_matching': True,
             # This video is no longer available, because its author has been blocked.
             'url': 'https://vk.com/video-10639516_456240611',
             'only_matching': True,

-        }
-    ]
+        },
+        {
+            # The video is not available in your region.
+            'url': 'https://vk.com/video-51812607_171445436',
+            'only_matching': True,
+        }]

 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
 
         if video_id:
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
 
         if video_id:

-            info_url = 'https://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id
+            info_url = 'https://vk.com/al_video.php?act=show_inline&al=1&video=' + video_id

             # Some videos (removed?) can only be downloaded with list id specified
             list_id = mobj.group('list_id')
             if list_id:
             # Some videos (removed?) can only be downloaded with list id specified
             list_id = mobj.group('list_id')
             if list_id:


@@ -317,9 +312,14 @@ class VKIE(VKBaseIE):
                 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
                 expected=True)
 
                 'You are trying to log in from an unusual location. You should confirm ownership at vk.com to log in with this IP.',
                 expected=True)
 

+        ERROR_COPYRIGHT = 'Video %s has been removed from public access due to rightholder complaint.'
+

         ERRORS = {
             r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':
         ERRORS = {
             r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<':

-            'Video %s has been removed from public access due to rightholder complaint.',
+            ERROR_COPYRIGHT,
+
+            r'>The video .*? was removed from public access by request of the copyright holder.<':
+            ERROR_COPYRIGHT,

 
             r'<!>Please log in or <':
             'Video %s is only available for registered users, '
 
             r'<!>Please log in or <':
             'Video %s is only available for registered users, '


@@ -339,17 +339,21 @@ class VKIE(VKBaseIE):
 
             r'<!>This video is no longer available, because its author has been blocked.':
             'Video %s is no longer available, because its author has been blocked.',
 
             r'<!>This video is no longer available, because its author has been blocked.':
             'Video %s is no longer available, because its author has been blocked.',

+
+            r'<!>This video is no longer available, because it has been deleted.':
+            'Video %s is no longer available, because it has been deleted.',
+
+            r'<!>The video .+? is not available in your region.':
+            'Video %s is not available in your region.',

         }
 
         for error_re, error_msg in ERRORS.items():
             if re.search(error_re, info_page):
                 raise ExtractorError(error_msg % video_id, expected=True)
 
         }
 
         for error_re, error_msg in ERRORS.items():
             if re.search(error_re, info_page):
                 raise ExtractorError(error_msg % video_id, expected=True)
 

-        youtube_url = self._search_regex(
-            r'<iframe[^>]+src="((?:https?:)?//www.youtube.com/embed/[^"]+)"',
-            info_page, 'youtube iframe', default=None)
+        youtube_url = YoutubeIE._extract_url(info_page)

         if youtube_url:
         if youtube_url:

-            return self.url_result(youtube_url, 'Youtube')
+            return self.url_result(youtube_url, ie=YoutubeIE.ie_key())

 
         vimeo_url = VimeoIE._extract_url(url, info_page)
         if vimeo_url is not None:
 
         vimeo_url = VimeoIE._extract_url(url, info_page)
         if vimeo_url is not None:


@@ -389,7 +393,8 @@ class VKIE(VKBaseIE):
         if not data:
             data = self._parse_json(
                 self._search_regex(
         if not data:
             data = self._parse_json(
                 self._search_regex(

-                    r'<!json>\s*({.+?})\s*<!>', info_page, 'json', default='{}'),
+                    [r'<!json>\s*({.+?})\s*<!>', r'<!json>\s*({.+})'],
+                    info_page, 'json', default='{}'),

                 video_id)
             if data:
                 data = data['player']['params'][0]
                 video_id)
             if data:
                 data = data['player']['params'][0]


@@ -398,8 +403,17 @@ class VKIE(VKBaseIE):
             data = self._parse_json(
                 self._search_regex(
                     r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,
             data = self._parse_json(
                 self._search_regex(
                     r'var\s+playerParams\s*=\s*({.+?})\s*;\s*\n', info_page,

-                    'player params'),
-                video_id)['params'][0]
+                    'player params', default='{}'),
+                video_id)
+            if data:
+                data = data['params'][0]
+
+        # <!--{...}
+        if not data:
+            data = self._parse_json(
+                self._search_regex(
+                    r'<!--\s*({.+})', info_page, 'payload'),
+                video_id)['payload'][-1][-1]['player']['params'][0]

 
         title = unescapeHTML(data['md_title'])
 
 
         title = unescapeHTML(data['md_title'])
 


@@ -411,18 +425,19 @@ class VKIE(VKBaseIE):
 
         timestamp = unified_timestamp(self._html_search_regex(
             r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,
 
         timestamp = unified_timestamp(self._html_search_regex(
             r'class=["\']mv_info_date[^>]+>([^<]+)(?:<|from)', info_page,

-            'upload date', fatal=False))
+            'upload date', default=None)) or int_or_none(data.get('date'))

 
         view_count = str_to_int(self._search_regex(
             r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',
 
         view_count = str_to_int(self._search_regex(
             r'class=["\']mv_views_count[^>]+>\s*([\d,.]+)',

-            info_page, 'view count', fatal=False))
+            info_page, 'view count', default=None))

 
         formats = []
         for format_id, format_url in data.items():
 
         formats = []
         for format_id, format_url in data.items():

-            if not isinstance(format_url, compat_str) or not format_url.startswith(('http', '//', 'rtmp')):
+            format_url = url_or_none(format_url)
+            if not format_url or not format_url.startswith(('http', '//', 'rtmp')):

                 continue
                 continue

-            if (format_id.startswith(('url', 'cache')) or
-                    format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):
+            if (format_id.startswith(('url', 'cache'))
+                    or format_id in ('extra_data', 'live_mp4', 'postlive_mp4')):

                 height = int_or_none(self._search_regex(
                     r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
                 formats.append({
                 height = int_or_none(self._search_regex(
                     r'^(?:url|cache)(\d+)', format_id, 'height', default=None))
                 formats.append({


@@ -432,8 +447,7 @@ class VKIE(VKBaseIE):
                 })
             elif format_id == 'hls':
                 formats.extend(self._extract_m3u8_formats(
                 })
             elif format_id == 'hls':
                 formats.extend(self._extract_m3u8_formats(

-                    format_url, video_id, 'mp4',
-                    entry_protocol='m3u8' if is_live else 'm3u8_native',
+                    format_url, video_id, 'mp4', 'm3u8_native',

                     m3u8_id=format_id, fatal=False, live=is_live))
             elif format_id == 'rtmp':
                 formats.append({
                     m3u8_id=format_id, fatal=False, live=is_live))
             elif format_id == 'rtmp':
                 formats.append({


@@ -444,14 +458,17 @@ class VKIE(VKBaseIE):
         self._sort_formats(formats)
 
         return {
         self._sort_formats(formats)
 
         return {

-            'id': compat_str(data.get('vid') or video_id),
+            'id': video_id,

             'formats': formats,
             'title': title,
             'thumbnail': data.get('jpg'),
             'uploader': data.get('md_author'),
             'formats': formats,
             'title': title,
             'thumbnail': data.get('jpg'),
             'uploader': data.get('md_author'),

+            'uploader_id': str_or_none(data.get('author_id')),

             'duration': data.get('duration'),
             'timestamp': timestamp,
             'view_count': view_count,
             'duration': data.get('duration'),
             'timestamp': timestamp,
             'view_count': view_count,

+            'like_count': int_or_none(data.get('liked')),
+            'dislike_count': int_or_none(data.get('nolikes')),

             'is_live': is_live,
         }
 
             'is_live': is_live,
         }