Merge pull request #1 from e7appew/python3

[youtubedl] / youtube_dl / extractor / rtl2.py

diff --git a/youtube_dl/extractor/rtl2.py b/youtube_dl/extractor/rtl2.py
index 72cd80498328ca4af9a9ac008afb16c5f0300c30..de004671d564eb455e45361666fd304f8ca040a6 100644 (file)
--- a/youtube_dl/extractor/rtl2.py
+++ b/youtube_dl/extractor/rtl2.py
@@ -1,6 +1,7 @@
 # encoding: utf-8
 from __future__ import unicode_literals
 
 # encoding: utf-8
 from __future__ import unicode_literals
 

+import re

 from .common import InfoExtractor
 
 
 from .common import InfoExtractor
 
 


@@ -8,22 +9,28 @@ class RTL2IE(InfoExtractor):
     _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
     _TESTS = [{
         'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',
     _VALID_URL = r'http?://(?:www\.)?rtl2\.de/[^?#]*?/(?P<id>[^?#/]*?)(?:$|/(?:$|[?#]))'
     _TESTS = [{
         'url': 'http://www.rtl2.de/sendung/grip-das-motormagazin/folge/folge-203-0',

-        'md5': 'bfcc179030535b08dc2b36b469b5adc7',

         'info_dict': {
             'id': 'folge-203-0',
             'ext': 'f4v',
             'title': 'GRIP sucht den Sommerkönig',
             'description': 'Matthias, Det und Helge treten gegeneinander an.'
         },
         'info_dict': {
             'id': 'folge-203-0',
             'ext': 'f4v',
             'title': 'GRIP sucht den Sommerkönig',
             'description': 'Matthias, Det und Helge treten gegeneinander an.'
         },

+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },

     }, {
         'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',
     }, {
         'url': 'http://www.rtl2.de/sendung/koeln-50667/video/5512-anna/21040-anna-erwischt-alex/',

-        'md5': 'ffcd517d2805b57ce11a58a2980c2b02',

         'info_dict': {
             'id': '21040-anna-erwischt-alex',
             'ext': 'mp4',
             'title': 'Anna erwischt Alex!',
             'description': 'Anna ist Alex\' Tochter bei Köln 50667.'
         },
         'info_dict': {
             'id': '21040-anna-erwischt-alex',
             'ext': 'mp4',
             'title': 'Anna erwischt Alex!',
             'description': 'Anna ist Alex\' Tochter bei Köln 50667.'
         },

+        'params': {
+            # rtmp download
+            'skip_download': True,
+        },

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


@@ -34,12 +41,18 @@ class RTL2IE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 

-        vico_id = self._html_search_regex(
-            r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
-        vivi_id = self._html_search_regex(
-            r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')
+        mobj = re.search(
+            r'<div[^>]+data-collection="(?P<vico_id>\d+)"[^>]+data-video="(?P<vivi_id>\d+)"',
+            webpage)
+        if mobj:
+            vico_id = mobj.group('vico_id')
+            vivi_id = mobj.group('vivi_id')
+        else:
+            vico_id = self._html_search_regex(
+                r'vico_id\s*:\s*([0-9]+)', webpage, 'vico_id')
+            vivi_id = self._html_search_regex(
+                r'vivi_id\s*:\s*([0-9]+)', webpage, 'vivi_id')

         info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id
         info_url = 'http://www.rtl2.de/video/php/get_video.php?vico_id=' + vico_id + '&vivi_id=' + vivi_id

-        webpage = self._download_webpage(info_url, '')

 
         info = self._download_json(info_url, video_id)
         video_info = info['video']
 
         info = self._download_json(info_url, video_id)
         video_info = info['video']


@@ -50,7 +63,7 @@ class RTL2IE(InfoExtractor):
         download_url = video_info['streamurl']
         download_url = download_url.replace('\\', '')
         stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL')
         download_url = video_info['streamurl']
         download_url = download_url.replace('\\', '')
         stream_url = 'mp4:' + self._html_search_regex(r'ondemand/(.*)', download_url, 'stream URL')

-        rtmp_conn = ["S:connect", "O:1", "NS:pageUrl:" + url, "NB:fpad:0", "NN:videoFunction:1", "O:0"]
+        rtmp_conn = ['S:connect', 'O:1', 'NS:pageUrl:' + url, 'NB:fpad:0', 'NN:videoFunction:1', 'O:0']

 
         formats = [{
             'url': download_url,
 
         formats = [{
             'url': download_url,