debian/copyright: Fix missing-license-paragraph-in-dep5-copyright.

[youtubedl] / youtube_dl / extractor / veehd.py

diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py
index 3a99a29c6520ba6824a9060264d678a5cf31e6e6..94647d1c8c88a18cfb6abcba2ec5ed8e71e9c4b6 100644 (file)
--- a/youtube_dl/extractor/veehd.py
+++ b/youtube_dl/extractor/veehd.py
@@ -1,3 +1,5 @@
+from __future__ import unicode_literals
+

 import re
 import json
 
 import re
 import json
 


@@ -8,16 +10,18 @@ from ..utils import (
     clean_html,
 )
 
     clean_html,
 )
 

+

 class VeeHDIE(InfoExtractor):
 class VeeHDIE(InfoExtractor):

-    _VALID_URL = r'https?://veehd.com/video/(?P<id>\d+)'
+    _VALID_URL = r'https?://veehd\.com/video/(?P<id>\d+)'

 
     _TEST = {
 
     _TEST = {

-        u'url': u'http://veehd.com/video/4686958',
-        u'file': u'4686958.mp4',
-        u'info_dict': {
-            u'title': u'Time Lapse View from Space ( ISS)',
-            u'uploader_id': u'spotted',
-            u'description': u'md5:f0094c4cf3a72e22bc4e4239ef767ad7',
+        'url': 'http://veehd.com/video/4686958',
+        'info_dict': {
+            'id': '4686958',
+            'ext': 'mp4',
+            'title': 'Time Lapse View from Space ( ISS)',
+            'uploader_id': 'spotted',
+            'description': 'md5:f0094c4cf3a72e22bc4e4239ef767ad7',

         },
     }
 
         },
     }
 


@@ -25,24 +29,30 @@ class VeeHDIE(InfoExtractor):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
 

+        # VeeHD seems to send garbage on the first request.
+        # See https://github.com/rg3/youtube-dl/issues/2102
+        self._download_webpage(url, video_id, 'Requesting webpage')

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

-        player_path = self._search_regex(r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
-            webpage, u'player path')
+        player_path = self._search_regex(
+            r'\$\("#playeriframe"\).attr\({src : "(.+?)"',
+            webpage, 'player path')

         player_url = compat_urlparse.urljoin(url, player_path)
         player_url = compat_urlparse.urljoin(url, player_path)

-        player_page = self._download_webpage(player_url, video_id,
-            u'Downloading player page')
-        config_json = self._search_regex(r'value=\'config=({.+?})\'',
-            player_page, u'config json')
+
+        self._download_webpage(player_url, video_id, 'Requesting player page')
+        player_page = self._download_webpage(
+            player_url, video_id, 'Downloading player page')
+        config_json = self._search_regex(
+            r'value=\'config=({.+?})\'', player_page, 'config json')

         config = json.loads(config_json)
 
         video_url = compat_urlparse.unquote(config['clip']['url'])
         title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
         uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>',
         config = json.loads(config_json)
 
         video_url = compat_urlparse.unquote(config['clip']['url'])
         title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
         uploader_id = self._html_search_regex(r'<a href="/profile/\d+">(.+?)</a>',

-            webpage, u'uploader')
+                                              webpage, 'uploader')

         thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"',
         thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"',

-            webpage, u'thumbnail')
+                                       webpage, 'thumbnail')

         description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul',
         description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul',

-            webpage, u'description', flags=re.DOTALL)
+                                              webpage, 'description', flags=re.DOTALL)

 
         return {
             '_type': 'video',
 
         return {
             '_type': 'video',