Merge tag 'upstream/2016.12.01'

[youtubedl] / youtube_dl / extractor / firsttv.py

diff --git a/youtube_dl/extractor/firsttv.py b/youtube_dl/extractor/firsttv.py
index 510d4b108944d1f220c45ddc2fbe85cdad6114ca..6b662cc3cd78e4acf661af473f2374b5ec2af05c 100644 (file)
--- a/youtube_dl/extractor/firsttv.py
+++ b/youtube_dl/extractor/firsttv.py
@@ -1,79 +1,93 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

-from ..utils import int_or_none
+from ..compat import compat_urlparse
+from ..utils import (
+    int_or_none,
+    qualities,
+    unified_strdate,
+)

 
 
 class FirstTVIE(InfoExtractor):
     IE_NAME = '1tv'
     IE_DESC = 'Первый канал'
 
 
 class FirstTVIE(InfoExtractor):
     IE_NAME = '1tv'
     IE_DESC = 'Первый канал'

-    _VALID_URL = r'http://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>.+)'
+    _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'

 
     _TESTS = [{
 
     _TESTS = [{

-        'url': 'http://www.1tv.ru/videoarchive/73390',
-        'md5': '777f525feeec4806130f4f764bc18a4f',
+        # single format
+        'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
+        'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',

         'info_dict': {
         'info_dict': {

-            'id': '73390',
+            'id': '40049',

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

-            'title': 'Ð\9eлимпийÑ\81кие канаÑ\82нÑ\8bе доÑ\80оги',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'title': 'Ð\93оÑ\81Ñ\82Ñ\8c Ð\9bÑ\8eдмила СенÑ\87ина. Ð\9dаедине Ñ\81о вÑ\81еми. Ð\92Ñ\8bпÑ\83Ñ\81к оÑ\82 12.02.2015',
+            'description': 'md5:36a39c1d19618fec57d12efe212a8370',

             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',

-            'duration': 149,
-            'like_count': int,
-            'dislike_count': int,
+            'upload_date': '20150212',
+            'duration': 2694,

         },
         },

-        'skip': 'Only works from Russia',

     }, {
     }, {

-        'url': 'http://www.1tv.ru/prj/inprivate/vypusk/35930',
-        'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
+        # multiple formats
+        'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',

         'info_dict': {
         'info_dict': {

-            'id': '35930',
+            'id': '364746',

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

-            'title': 'Ð\9dаедине Ñ\81о вÑ\81еми. Ð\9bÑ\8eдмила СенÑ\87ина',
-            'description': 'md5:89553aed1d641416001fe8d450f06cb9',
+            'title': 'Ð\92еÑ\81еннÑ\8fÑ\8f аллеÑ\80гиÑ\8f. Ð\94обÑ\80ое Ñ\83Ñ\82Ñ\80о. ФÑ\80агменÑ\82 вÑ\8bпÑ\83Ñ\81ка оÑ\82 07.04.2016',
+            'description': 'md5:a242eea0031fd180a4497d52640a9572',

             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
             'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',

-            'duration': 2694,
+            'upload_date': '20160407',
+            'duration': 179,
+            'formats': 'mincount:3',
+        },
+        'params': {
+            'skip_download': True,

         },
         },

-        'skip': 'Only works from Russia',

     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):

-        video_id = self._match_id(url)
+        display_id = self._match_id(url)

 
 

-        webpage = self._download_webpage(url, video_id, 'Downloading page')
+        webpage = self._download_webpage(url, display_id)
+        playlist_url = compat_urlparse.urljoin(url, self._search_regex(
+            r'data-playlist-url="([^"]+)', webpage, 'playlist url'))

 
 

-        video_url = self._html_search_regex(
-            r'''(?s)(?:jwplayer\('flashvideoportal_1'\)\.setup\({|var\s+playlistObj\s*=).*?'file'\s*:\s*'([^']+)'.*?}\);''',
-            webpage, 'video URL')
+        item = self._download_json(playlist_url, display_id)[0]
+        video_id = item['id']
+        quality = qualities(('ld', 'sd', 'hd', ))
+        formats = []
+        for f in item.get('mbr', []):
+            src = f.get('src')
+            if not src:
+                continue
+            fname = f.get('name')
+            formats.append({
+                'url': src,
+                'format_id': fname,
+                'quality': quality(fname),
+            })
+        self._sort_formats(formats)

 
         title = self._html_search_regex(
 
         title = self._html_search_regex(

-            [r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
-             r"'title'\s*:\s*'([^']+)'"], webpage, 'title')
+            (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
+             r"'title'\s*:\s*'([^']+)'"),
+            webpage, 'title', default=None) or item['title']

         description = self._html_search_regex(
             r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
             webpage, 'description', default=None) or self._html_search_meta(
         description = self._html_search_regex(
             r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
             webpage, 'description', default=None) or self._html_search_meta(

-                'description', webpage, 'description')
-
-        thumbnail = self._og_search_thumbnail(webpage)
-        duration = self._og_search_property(
-            'video:duration', webpage,
-            'video duration', fatal=False)
-
-        like_count = self._html_search_regex(
-            r'title="Понравилось".*?/></label> \[(\d+)\]',
-            webpage, 'like count', default=None)
-        dislike_count = self._html_search_regex(
-            r'title="Не понравилось".*?/></label> \[(\d+)\]',
-            webpage, 'dislike count', default=None)
+            'description', webpage, 'description')
+        duration = int_or_none(self._html_search_meta(
+            'video:duration', webpage, 'video duration', fatal=False))
+        upload_date = unified_strdate(self._html_search_meta(
+            'ya:ovs:upload_date', webpage, 'upload date', fatal=False))

 
         return {
             'id': video_id,
 
         return {
             'id': video_id,

-            'url': video_url,
-            'thumbnail': thumbnail,
+            'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),

             'title': title,
             'description': description,
             'title': title,
             'description': description,

+            'upload_date': upload_date,

             'duration': int_or_none(duration),
             'duration': int_or_none(duration),

-            'like_count': int_or_none(like_count),
-            'dislike_count': int_or_none(dislike_count),
+            'formats': formats

         }
         }