Merge pull request #1 from e7appew/python3

[youtubedl] / youtube_dl / extractor / vier.py

diff --git a/youtube_dl/extractor/vier.py b/youtube_dl/extractor/vier.py
index 15377097e658b20e75a08f19b370be3bef2158c7..6645c6186dbff315e850f22ae793677803cbbf9b 100644 (file)
--- a/youtube_dl/extractor/vier.py
+++ b/youtube_dl/extractor/vier.py
@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 import re
+import itertools
 
 from .common import InfoExtractor
 
@@ -49,6 +50,7 @@ class VierIE(InfoExtractor):
 
         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')
+        self._sort_formats(formats)
 
         title = self._og_search_title(webpage, default=display_id)
         description = self._og_search_description(webpage, default=None)
@@ -91,31 +93,27 @@ class VierVideosIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         program = mobj.group('program')
 
-        webpage = self._download_webpage(url, program)
-
         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
-            last_page = int(self._search_regex(
-                r'videos\?page=(\d+)">laatste</a>',
-                webpage, 'last page', default=0)) + 1
             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(
                 'http://www.vier.be/%s/videos?page=%d' % (program, current_page_id),
                 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 = [
                 self.url_result('http://www.vier.be' + video_url, 'Vier')
                 for video_url in re.findall(
                     r'<h3><a href="(/[^/]+/videos/[^/]+(?:/\d+)?)">', current_page)]
             entries.extend(page_entries)
+            if page_id or '>Meer<' not in current_page:
+                break
 
         return self.playlist_result(entries, playlist_id)