New upstream version 2017.03.26

[youtubedl] / youtube_dl / extractor / vier.py

diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py
index 619039e516c96209c38953e6b73f93a6895df54c..5086f591e56b6b6a9266e96b3c26541963757120 100644 (file)
--- a/youtube_dl/extractor/vier.py
+++ b/youtube_dl/extractor/vier.py
@@ -2,13 +2,14 @@
 from __future__ import unicode_literals
 
 import re
 from __future__ import unicode_literals
 
 import re

+import itertools

 
 from .common import InfoExtractor
 
 
 class VierIE(InfoExtractor):
     IE_NAME = 'vier'
 
 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': {
     _TESTS = [{
         'url': 'http://www.vier.be/planb/videos/het-wordt-warm-de-moestuin/16129',
         'info_dict': {


@@ -22,6 +23,19 @@ class VierIE(InfoExtractor):
             # m3u8 download
             'skip_download': True,
         },
             # m3u8 download
             '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,
     }, {
         'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
         'only_matching': True,


@@ -34,18 +48,23 @@ 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
         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)
 
         video_id = self._search_regex(
 
         webpage = self._download_webpage(url, display_id)
 
         video_id = self._search_regex(

-            r'"nid"\s*:\s*"(\d+)"', webpage, 'video id')
+            [r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'],
+            webpage, 'video id')

         application = self._search_regex(
         application = self._search_regex(

-            r'"application"\s*:\s*"([^"]+)"', webpage, 'application', default='vier_vod')
+            [r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'],
+            webpage, 'application', default=site + '_vod')

         filename = self._search_regex(
         filename = self._search_regex(

-            r'"filename"\s*:\s*"([^"]+)"', webpage, 'filename')
+            [r'data-filename="([^"]+)"', r'"filename"\s*:\s*"([^"]+)"'],
+            webpage, 'filename')

 
 

-        playlist_url = 'http://vod.streamcloud.be/%s/mp4:_definst_/%s.mp4/playlist.m3u8' % (application, filename)
-        formats = self._extract_m3u8_formats(playlist_url, display_id, 'mp4')
+        playlist_url = 'http://vod.streamcloud.be/%s/_definst_/mp4:%s.mp4/playlist.m3u8' % (application, filename)
+        formats = self._extract_wowza_formats(playlist_url, display_id, skip_protocols=['dash'])
+        self._sort_formats(formats)

 
         title = self._og_search_title(webpage, default=display_id)
         description = self._og_search_description(webpage, default=None)
 
         title = self._og_search_title(webpage, default=display_id)
         description = self._og_search_description(webpage, default=None)


@@ -63,13 +82,19 @@ class VierIE(InfoExtractor):
 
 class VierVideosIE(InfoExtractor):
     IE_NAME = 'vier:videos'
 
 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': {
             'id': 'demoestuin',
         },
         'playlist_mincount': 153,
     _TESTS = [{
         'url': 'http://www.vier.be/demoestuin/videos',
         'info_dict': {
             'id': 'demoestuin',
         },
         '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': {
     }, {
         'url': 'http://www.vier.be/demoestuin/videos?page=6',
         'info_dict': {


@@ -87,32 +112,29 @@ class VierVideosIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         program = mobj.group('program')
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         program = mobj.group('program')

-
-        webpage = self._download_webpage(url, program)
+        site = mobj.group('site')

 
         page_id = mobj.group('page')
         if page_id:
             page_id = int(page_id)
             start_page = page_id
 
         page_id = mobj.group('page')
         if page_id:
             page_id = int(page_id)
             start_page = page_id

-            last_page = start_page + 1

             playlist_id = '%s-page%d' % (program, page_id)
         else:
             start_page = 0
             playlist_id = '%s-page%d' % (program, page_id)
         else:
             start_page = 0

-            last_page = int(self._search_regex(
-                r'videos\?page=(\d+)">laatste</a>',
-                webpage, 'last page', default=0)) + 1

             playlist_id = program
 
         entries = []
             playlist_id = program
 
         entries = []

-        for current_page_id in range(start_page, last_page):
+        for current_page_id in itertools.count(start_page):

             current_page = self._download_webpage(
             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,
                 program,

-                'Downloading page %d' % (current_page_id + 1)) if current_page_id != page_id else webpage
+                'Downloading page %d' % (current_page_id + 1))

             page_entries = [
             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(
                 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)
             entries.extend(page_entries)

+            if page_id or '>Meer<' not in current_page:
+                break

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