youtube-dl

commit a3ba8a7acfa2db3a8c90000d377c25d14bdad290
parent 054a587de8fe2860bcb93a19f8c628b4ddd9ad56
Author: Lars Vierbergen <vierbergenlars@gmail.com>
Date:   Sat,  4 Mar 2017 17:47:19 +0100

[vier] Add support for vijf.be

vier.be and vijf.be run on the same CMS and are property of the same company,
so the same extractor can be used for both of them.
Diffstat:
M
youtube_dl/extractor/vier.py
 | 
33
+++++++++++++++++++++++++++------

1 file changed, 27 insertions(+), 6 deletions(-)
diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py
@@ -9,7 +9,7 @@ from .common import InfoExtractor
 
 class VierIE(InfoExtractor):
     IE_NAME = 'vier'
-    _VALID_URL = r'https?://(?:www\.)?vier\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?:[^/]+/videos/(?P<display_id>[^/]+)(?:/(?P<id>\d+))?|video/v3/embed/(?P<embed_id>\d+))'
     _TESTS = [{
         'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
         'info_dict': {
@@ -24,6 +24,19 @@ class VierIE(InfoExtractor):
             'skip_download': True,
         },
     }, {
+        'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614',
+        'info_dict': {
+            'id': '2561614',
+            'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas',
+            'ext': 'mp4',
+            'title': 'ZO grappig: Temptation Island hosts moeten kiezen tussen onmogelijke dilemma\'s',
+            'description': 'Het spel is simpel: Annelien Coorevits en Rick Brandsteder krijgen telkens 2 dilemma\'s voorgeschoteld en ze MOETEN een keuze maken.',
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+    }, {
         'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
         'only_matching': True,
     }, {
@@ -35,6 +48,7 @@ class VierIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         embed_id = mobj.group('embed_id')
         display_id = mobj.group('display_id') or embed_id
+        site = mobj.group('site')
 
         webpage = self._download_webpage(url, display_id)
 
@@ -43,7 +57,7 @@ class VierIE(InfoExtractor):
             webpage, 'video id')
         application = self._search_regex(
             [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'],
-            webpage, 'application', default='vier_vod')
+            webpage, 'application', default=site + '_vod')
         filename = self._search_regex(
             [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'],
             webpage, 'filename')
@@ -68,7 +82,7 @@ class VierIE(InfoExtractor):
 
 class VierVideosIE(InfoExtractor):
     IE_NAME = 'vier:videos'
-    _VALID_URL = r'https?://(?:www\.)?vier\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<site>vier|vijf)\.be/(?P<program>[^/]+)/videos(?:\?.*\bpage=(?P<page>\d+)|$)'
     _TESTS = [{
         'url': 'http://www.vier.be/demoestuin/videos',
         'info_dict': {
@@ -76,6 +90,12 @@ class VierVideosIE(InfoExtractor):
         },
         'playlist_mincount': 153,
     }, {
+        'url': 'http://www.vijf.be/temptationisland/videos',
+        'info_dict': {
+            'id': 'temptationisland',
+        },
+        'playlist_mincount': 159,
+    }, {
         'url': 'http://www.vier.be/demoestuin/videos?page=6',
         'info_dict': {
             'id': 'demoestuin-page6',
@@ -92,6 +112,7 @@ class VierVideosIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         program = mobj.group('program')
+        site = mobj.group('site')
 
         page_id = mobj.group('page')
         if page_id:
@@ -105,13 +126,13 @@ class VierVideosIE(InfoExtractor):
         entries = []
         for current_page_id in itertools.count(start_page):
             current_page = self._download_webpage(
-                'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
+                'http://www.%s.be/%s/videos?page=%d' % (site, program, current_page_id),
                 program,
                 'Downloading page %d' % (current_page_id + 1))
             page_entries = [
-                self.url_result('http://www.vier.be' + video_url, 'Vier')
+                self.url_result('http://www.' + site + '.be' + video_url, 'Vier')
                 for video_url in re.findall(
-                    r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
+                    r'<h[23]><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
             entries.extend(page_entries)
             if page_id or '>Meer<' not in current_page:
                 break