Merge tag 'upstream/2015.02.06'

[youtubedl] / youtube_dl / extractor / veehd.py

diff --git a/youtube_dl/extractor/veehd.py b/youtube_dl/extractor/veehd.py
index 3a99a29c6520ba6824a9060264d678a5cf31e6e6..96353f5250783be95fd4bf308190309baae70187 100644 (file)
--- a/youtube_dl/extractor/veehd.py
+++ b/youtube_dl/extractor/veehd.py
@@ -1,48 +1,81 @@
+from __future__ import unicode_literals
+

 import re
 import json
 
 from .common import InfoExtractor
 import re
 import json
 
 from .common import InfoExtractor

-from ..utils import (
+from ..compat import (

     compat_urlparse,
     compat_urlparse,

-    get_element_by_id,
+)
+from ..utils import (
+    ExtractorError,

     clean_html,
     clean_html,

+    get_element_by_id,

 )
 
 )
 

+

 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/4639434_Solar-Sinter',
+        'info_dict': {
+            'id': '4639434',
+            'ext': 'mp4',
+            'title': 'Solar Sinter',
+            'uploader_id': 'VideoEyes',
+            'description': 'md5:46a840e8692ddbaffb5f81d9885cb457',

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

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

 
 

+        # 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')
+
+        if 'This video has been removed<' in webpage:
+            raise ExtractorError('Video %s has been removed' % video_id, expected=True)
+
+        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')
-        config = json.loads(config_json)

 
 

-        video_url = compat_urlparse.unquote(config['clip']['url'])
+        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', default=None)
+
+        if config_json:
+            config = json.loads(config_json)
+            video_url = compat_urlparse.unquote(config['clip']['url'])
+        else:
+            iframe_src = self._search_regex(
+                r'<iframe[^>]+src="/?([^"]+)"', player_page, 'iframe url')
+            iframe_url = 'http://veehd.com/%s' % iframe_src
+
+            self._download_webpage(iframe_url, video_id, 'Requesting iframe page')
+            iframe_page = self._download_webpage(
+                iframe_url, video_id, 'Downloading iframe page')
+
+            video_url = self._search_regex(
+                r"file\s*:\s*'([^']+)'", iframe_page, 'video url')
+

         title = clean_html(get_element_by_id('videoName', webpage).rpartition('|')[0])
         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')
-        thumbnail = self._search_regex(r'<img id="veehdpreview" src="(.+?)"',
-            webpage, u'thumbnail')
-        description = self._html_search_regex(r'<td class="infodropdown".*?<div>(.*?)<ul',
-            webpage, u'description', flags=re.DOTALL)
+        uploader_id = self._html_search_regex(
+            r'<a href="/profile/\d+">(.+?)</a>',
+            webpage, 'uploader')
+        thumbnail = self._search_regex(
+            r'<img id="veehdpreview" src="(.+?)"',
+            webpage, 'thumbnail')
+        description = self._html_search_regex(
+            r'<td class="infodropdown".*?<div>(.*?)<ul',
+            webpage, 'description', flags=re.DOTALL)

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