debian/control: Add recommends on aria2 | wget | curl to use external downloaders.

[youtubedl] / youtube_dl / extractor / extremetube.py

diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
index 14a196ffc63336ae7d016b035cfb28cc7f7d28a0..36ba331285b434136b8d3c10e6a8a16bef18e7b7 100644 (file)
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@@ -3,15 +3,18 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

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

     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
 )
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
 )

+from ..utils import (
+    str_to_int,
+)

 
 
 class ExtremeTubeIE(InfoExtractor):
 
 
 class ExtremeTubeIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<videoid>[0-9]+))(?:[/?&]|$)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>extremetube\.com/.*?video/.+?(?P<id>[0-9]+))(?:[/?&]|$)'

     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
         'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',
     _TESTS = [{
         'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431',
         'md5': '1fb9228f5e3332ec8c057d6ac36f33e0',


@@ -20,6 +23,7 @@ class ExtremeTubeIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',

+            'view_count': int,

             'age_limit': 18,
         }
     }, {
             'age_limit': 18,
         }
     }, {


@@ -29,7 +33,7 @@ class ExtremeTubeIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group('videoid')
+        video_id = mobj.group('id')

         url = 'http://www.' + mobj.group('url')
 
         req = compat_urllib_request.Request(url)
         url = 'http://www.' + mobj.group('url')
 
         req = compat_urllib_request.Request(url)


@@ -39,8 +43,12 @@ class ExtremeTubeIE(InfoExtractor):
         video_title = self._html_search_regex(
             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(
         video_title = self._html_search_regex(
             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(

-            r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
-            fatal=False)
+            r'Uploaded by:\s*</strong>\s*(.+?)\s*</div>',
+            webpage, 'uploader', fatal=False)
+        view_count = str_to_int(self._html_search_regex(
+            r'Views:\s*</strong>\s*<span>([\d,\.]+)</span>',
+            webpage, 'view count', fatal=False))
+

         video_url = compat_urllib_parse.unquote(self._html_search_regex(
             r'video_url=(.+?)&amp;', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path
         video_url = compat_urllib_parse.unquote(self._html_search_regex(
             r'video_url=(.+?)&amp;', webpage, 'video_url'))
         path = compat_urllib_parse_urlparse(video_url).path


@@ -51,6 +59,7 @@ class ExtremeTubeIE(InfoExtractor):
             'id': video_id,
             'title': video_title,
             'uploader': uploader,
             'id': video_id,
             'title': video_title,
             'uploader': uploader,

+            'view_count': view_count,

             'url': video_url,
             'format': format,
             'format_id': format,
             'url': video_url,
             'format': format,
             'format_id': format,