Merge branch 'douyutv' of https://github.com/bonfy/youtube-dl into bonfy-douyutv

[youtube-dl] / youtube_dl / extractor / extremetube.py

diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py
index 14a196ffc63336ae7d016b035cfb28cc7f7d28a0..c826a5404a4f7da298927460f1f8e41dd013d3a7 100644 (file)
--- a/youtube_dl/extractor/extremetube.py
+++ b/youtube_dl/extractor/extremetube.py
@@ -3,23 +3,27 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse_urlparse,
+from ..compat import (
+    compat_parse_qs,
     compat_urllib_request,
-    compat_urllib_parse,
+)
+from ..utils import (
+    qualities,
+    str_to_int,
 )
 
 
 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',
+        'md5': '344d0c6d50e2f16b06e49ca011d8ac69',
         'info_dict': {
             'id': '652431',
             'ext': 'mp4',
             'title': 'Music Video 14 british euro brit european cumshots swallow',
             'uploader': 'unknown',
+            'view_count': int,
             'age_limit': 18,
         }
     }, {
@@ -29,7 +33,7 @@ class ExtremeTubeIE(InfoExtractor):
 
     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)
@@ -39,20 +43,33 @@ class ExtremeTubeIE(InfoExtractor):
         video_title = self._html_search_regex(
             r'<h1 [^>]*?title="([^"]+)"[^>]*>', webpage, 'title')
         uploader = self._html_search_regex(
-            r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader',
-            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
-        format = path.split('/')[5].split('_')[:2]
-        format = "-".join(format)
+            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))
+
+        flash_vars = compat_parse_qs(self._search_regex(
+            r'<param[^>]+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars'))
+
+        formats = []
+        quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p'])
+        for k, vals in flash_vars.items():
+            m = re.match(r'quality_(?P<quality>[0-9]+p)$', k)
+            if m is not None:
+                formats.append({
+                    'format_id': m.group('quality'),
+                    'quality': quality(m.group('quality')),
+                    'url': vals[0],
+                })
+
+        self._sort_formats(formats)
 
         return {
             'id': video_id,
             'title': video_title,
+            'formats': formats,
             'uploader': uploader,
-            'url': video_url,
-            'format': format,
-            'format_id': format,
+            'view_count': view_count,
             'age_limit': 18,
         }