debian/control: Add recommends on aria2 | wget | curl to use external downloaders.

[youtubedl] / youtube_dl / extractor / wdr.py

diff --git a/youtube_dl/extractor/wdr.py b/youtube_dl/extractor/wdr.py
index feeb44b45ff32b4738957e44a6603cde93c8b9a4..c9048850061e1ecae4380557503a6b3927d2220c 100644 (file)
--- a/youtube_dl/extractor/wdr.py
+++ b/youtube_dl/extractor/wdr.py
@@ -1,11 +1,15 @@
+# -*- coding: utf-8 -*-

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

+import itertools

 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_parse_qs,
     compat_urlparse,
     compat_parse_qs,
     compat_urlparse,

+)
+from ..utils import (

     determine_ext,
     unified_strdate,
 )
     determine_ext,
     unified_strdate,
 )


@@ -54,16 +58,23 @@ class WDRIE(InfoExtractor):
             },
         },
         {
             },
         },
         {

-            'url': 'http://www.funkhauseuropa.de/av/audiogrenzenlosleckerbaklava101-audioplayer.html',
-            'md5': 'cfff440d4ee64114083ac44676df5d15',
+            'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
+            'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',

             'info_dict': {
             'info_dict': {

-                'id': 'mdb-363068',
+                'id': 'mdb-478135',

                 'ext': 'mp3',
                 'ext': 'mp3',

-                'title': 'Grenzenlos lecker - Baklava',
+                'title': 'Flavia Coelho: Amar é Amar',

                 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
                 'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',

-                'upload_date': '20140311',
+                'upload_date': '20140717',

             },
         },
             },
         },

+        {
+            'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
+            'playlist_mincount': 146,
+            'info_dict': {
+                'id': 'mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100',
+            }
+        }

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


@@ -78,9 +89,30 @@ class WDRIE(InfoExtractor):
                 self.url_result(page_url + href, 'WDR')
                 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
             ]
                 self.url_result(page_url + href, 'WDR')
                 for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
             ]

+
+            if entries:  # Playlist page
+                return self.playlist_result(entries, page_id)
+
+            # Overview page
+            entries = []
+            for page_num in itertools.count(2):
+                hrefs = re.findall(
+                    r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
+                    webpage)
+                entries.extend(
+                    self.url_result(page_url + href, 'WDR')
+                    for href in hrefs)
+                next_url_m = re.search(
+                    r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
+                if not next_url_m:
+                    break
+                next_url = page_url + next_url_m.group(1)
+                webpage = self._download_webpage(
+                    next_url, page_id,
+                    note='Downloading playlist page %d' % page_num)

             return self.playlist_result(entries, page_id)
 
             return self.playlist_result(entries, page_id)
 

-        flashvars = compat_urlparse.parse_qs(
+        flashvars = compat_parse_qs(

             self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
 
         page_id = flashvars['trackerClipId'][0]
             self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
 
         page_id = flashvars['trackerClipId'][0]


@@ -127,9 +159,10 @@ class WDRMobileIE(InfoExtractor):
         'info_dict': {
             'title': '4283021',
             'id': '421735',
         'info_dict': {
             'title': '4283021',
             'id': '421735',

+            'ext': 'mp4',

             'age_limit': 0,
         },
             'age_limit': 0,
         },

-        '_skip': 'Will be depublicized shortly'
+        'skip': 'Problems with loading data.'

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


@@ -139,7 +172,9 @@ class WDRMobileIE(InfoExtractor):
             'title': mobj.group('title'),
             'age_limit': int(mobj.group('age_limit')),
             'url': url,
             'title': mobj.group('title'),
             'age_limit': int(mobj.group('age_limit')),
             'url': url,

-            'user_agent': 'mobile',
+            'http_headers': {
+                'User-Agent': 'mobile',
+            },

         }
 
 
         }
 
 


@@ -168,8 +203,7 @@ class WDRMausIE(InfoExtractor):
     }]
 
     def _real_extract(self, url):
     }]
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

 
         webpage = self._download_webpage(url, video_id)
         param_code = self._html_search_regex(
 
         webpage = self._download_webpage(url, video_id)
         param_code = self._html_search_regex(


@@ -220,5 +254,3 @@ class WDRMausIE(InfoExtractor):
             'thumbnail': thumbnail,
             'upload_date': upload_date,
         }
             'thumbnail': thumbnail,
             'upload_date': upload_date,
         }

-
-# TODO test _1
\ No newline at end of file