Imported Upstream version 2016.02.22

[youtubedl] / youtube_dl / extractor / wdr.py

diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py
index b468023060d3476e0a0ede8e36ea23b25ffeb298..a851578e075589e6b36d828135f9919a9f1d0c38 100644 (file)
--- a/youtube_dl/extractor/wdr.py
+++ b/youtube_dl/extractor/wdr.py
@@ -10,8 +10,8 @@ from ..compat import (
     compat_urlparse,
 )
 from ..utils import (
-    determine_ext,
     unified_strdate,
+    qualities,
 )
 
 
@@ -33,6 +33,7 @@ class WDRIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
+            'skip': 'Page Not Found',
         },
         {
             'url': 'http://www1.wdr.de/themen/av/videomargaspiegelisttot101-videoplayer.html',
@@ -47,6 +48,7 @@ class WDRIE(InfoExtractor):
             'params': {
                 'skip_download': True,
             },
+            'skip': 'Page Not Found',
         },
         {
             'url': 'http://www1.wdr.de/themen/kultur/audioerlebtegeschichtenmargaspiegel100-audioplayer.html',
@@ -71,6 +73,7 @@ class WDRIE(InfoExtractor):
                 'upload_date': '20140717',
                 'is_live': False
             },
+            'skip': 'Page Not Found',
         },
         {
             'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
@@ -83,10 +86,10 @@ class WDRIE(InfoExtractor):
             'url': 'http://www1.wdr.de/mediathek/video/livestream/index.html',
             'info_dict': {
                 'id': 'mdb-103364',
-                'title': 're:^WDR Fernsehen [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+                'title': 're:^WDR Fernsehen Live [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
                 'description': 'md5:ae2ff888510623bf8d4b115f95a9b7c9',
                 'ext': 'flv',
-                'upload_date': '20150212',
+                'upload_date': '20150101',
                 'is_live': True
             },
             'params': {
@@ -105,7 +108,9 @@ class WDRIE(InfoExtractor):
         if mobj.group('player') is None:
             entries = [
                 self.url_result(page_url + href, 'WDR')
-                for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
+                for href in re.findall(
+                    r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX,
+                    webpage)
             ]
 
             if entries:  # Playlist page
@@ -130,8 +135,8 @@ class WDRIE(InfoExtractor):
                     note='Downloading playlist page %d' % page_num)
             return self.playlist_result(entries, page_id)
 
-        flashvars = compat_parse_qs(
-            self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
+        flashvars = compat_parse_qs(self._html_search_regex(
+            r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
 
         page_id = flashvars['trackerClipId'][0]
         video_url = flashvars['dslSrc'][0]
@@ -145,30 +150,60 @@ class WDRIE(InfoExtractor):
         if 'trackerClipAirTime' in flashvars:
             upload_date = flashvars['trackerClipAirTime'][0]
         else:
-            upload_date = self._html_search_meta('DC.Date', webpage, 'upload date')
+            upload_date = self._html_search_meta(
+                'DC.Date', webpage, 'upload date')
 
         if upload_date:
             upload_date = unified_strdate(upload_date)
 
+        formats = []
+        preference = qualities(['S', 'M', 'L', 'XL'])
+
         if video_url.endswith('.f4m'):
-            video_url += '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18'
-            ext = 'flv'
+            formats.extend(self._extract_f4m_formats(
+                video_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18', page_id,
+                f4m_id='hds', fatal=False))
         elif video_url.endswith('.smil'):
-            fmt = self._extract_smil_formats(video_url, page_id)[0]
-            video_url = fmt['url']
-            sep = '&' if '?' in video_url else '?'
-            video_url += sep
-            video_url += 'hdcore=3.3.0&plugin=aasp-3.3.0.99.43'
-            ext = fmt['ext']
+            formats.extend(self._extract_smil_formats(
+                video_url, page_id, False, {
+                    'hdcore': '3.3.0',
+                    'plugin': 'aasp-3.3.0.99.43',
+                }))
         else:
-            ext = determine_ext(video_url)
+            formats.append({
+                'url': video_url,
+                'http_headers': {
+                    'User-Agent': 'mobile',
+                },
+            })
+
+        m3u8_url = self._search_regex(
+            r'rel="adaptiv"[^>]+href="([^"]+)"',
+            webpage, 'm3u8 url', default=None)
+        if m3u8_url:
+            formats.extend(self._extract_m3u8_formats(
+                m3u8_url, page_id, 'mp4', 'm3u8_native',
+                m3u8_id='hls', fatal=False))
+
+        direct_urls = re.findall(
+            r'rel="web(S|M|L|XL)"[^>]+href="([^"]+)"', webpage)
+        if direct_urls:
+            for quality, video_url in direct_urls:
+                formats.append({
+                    'url': video_url,
+                    'preference': preference(quality),
+                    'http_headers': {
+                        'User-Agent': 'mobile',
+                    },
+                })
+
+        self._sort_formats(formats)
 
         description = self._html_search_meta('Description', webpage, 'description')
 
         return {
             'id': page_id,
-            'url': video_url,
-            'ext': ext,
+            'formats': formats,
             'title': title,
             'description': description,
             'thumbnail': thumbnail,