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 08ceee4ed7d5e8b96b81e7d8b9b823a5ea18e120..6b662cc3cd78e4acf661af473f2374b5ec2af05c 100644 (file)
--- a/youtube_dl/extractor/firsttv.py
+++ b/youtube_dl/extractor/firsttv.py
@@ -1,60 +1,93 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import re
-

 from .common import InfoExtractor
 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):
 
 
 class FirstTVIE(InfoExtractor):

-    IE_NAME = 'firsttv'
-    IE_DESC = 'Ð\92идеоаÑ\80Ñ\85ив - Ð\9fеÑ\80вÑ\8bй канал'
-    _VALID_URL = r'http://(?:www\.)?1tv\.ru/videoarchive/(?P<id>\d+)'
+    IE_NAME = '1tv'
+    IE_DESC = 'Первый канал'
+    _VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'

 
 

-    _TEST = {
-        'url': 'http://www.1tv.ru/videoarchive/73390',
-        'md5': '3de6390cf0cca4a5eae1d1d83895e5ad',
+    _TESTS = [{
+        # 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': {
+            'id': '40049',
+            'ext': 'mp4',
+            'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
+            'description': 'md5:36a39c1d19618fec57d12efe212a8370',
+            'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
+            'upload_date': '20150212',
+            'duration': 2694,
+        },
+    }, {
+        # 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': '73390',
+            'id': '364746',

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

-            'title': 'Олимпийские канатные дороги',
-            'description': 'md5:cc730d2bf4215463e37fff6a1e277b13',
-            'thumbnail': 'http://img1.1tv.ru/imgsize640x360/PR20140210114657.JPG',
-            'duration': 149,
+            'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
+            'description': 'md5:a242eea0031fd180a4497d52640a9572',
+            'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
+            'upload_date': '20160407',
+            'duration': 179,
+            'formats': 'mincount:3',

         },
         },

-        'skip': 'Only works from Russia',
-    }
+        'params': {
+            'skip_download': True,
+        },
+    }]

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

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        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\({.*?'file': '([^']+)'.*?}\);''', 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>', 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(
         description = self._html_search_regex(

-            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>', webpage, 'description', fatal=False)
-
-        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', fatal=False)
-        dislike_count = self._html_search_regex(r'title="Не понравилось".*?/></label> \[(\d+)\]',
-                                                webpage, 'dislike count', fatal=False)
+            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
+            webpage, 'description', default=None) or self._html_search_meta(
+            '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

         }
         }