]> Raphaƫl G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/spankwire.py
Set upstream metadata fields: Bug-Database, Bug-Submit, Repository, Repository-Browse.
[youtubedl] / youtube_dl / extractor / spankwire.py
index 2007a00134dfe73cd721dbee9e86e4f349a2e034..44d8fa52f3071ca00971624db81ce4ad6b2141e3 100644 (file)
@@ -3,20 +3,22 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
+    compat_urllib_parse_unquote,
     compat_urllib_parse_urlparse,
-    compat_urllib_request,
-    compat_urllib_parse,
-    unified_strdate,
+)
+from ..utils import (
+    sanitized_Request,
     str_to_int,
-    int_or_none,
+    unified_strdate,
 )
 from ..aes import aes_decrypt_text
 
 
 class SpankwireIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
-    _TEST = {
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<id>[0-9]+)/?)'
+    _TESTS = [{
+        # download URL pattern: */<height>P_<tbr>K_<video_id>.mp4
         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
         'md5': '8bbfde12b101204b39e4b9fe7eb67095',
         'info_dict': {
@@ -26,61 +28,85 @@ class SpankwireIE(InfoExtractor):
             'description': 'Crazy Bitch X rated music video.',
             'uploader': 'oreusz',
             'uploader_id': '124697',
-            'upload_date': '20070508',
+            'upload_date': '20070507',
             'age_limit': 18,
         }
-    }
+    }, {
+        # download URL pattern: */mp4_<format_id>_<video_id>.mp4
+        'url': 'http://www.spankwire.com/Titcums-Compiloation-I/video1921551/',
+        'md5': '09b3c20833308b736ae8902db2f8d7e6',
+        'info_dict': {
+            'id': '1921551',
+            'ext': 'mp4',
+            'title': 'Titcums Compiloation I',
+            'description': 'cum on tits',
+            'uploader': 'dannyh78999',
+            'uploader_id': '3056053',
+            'upload_date': '20150822',
+            'age_limit': 18,
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('videoid')
-        url = 'http://www.' + mobj.group('url')
+        video_id = mobj.group('id')
 
-        req = compat_urllib_request.Request(url)
+        req = sanitized_Request('http://www.' + mobj.group('url'))
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
-        title = self._html_search_regex(r'<h1>([^<]+)', webpage, 'title')
+        title = self._html_search_regex(
+            r'<h1>([^<]+)', webpage, 'title')
         description = self._html_search_regex(
-            r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False)
+            r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
+            webpage, 'description', fatal=False)
         thumbnail = self._html_search_regex(
-            r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
+            r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
+            webpage, 'thumbnail', fatal=False)
 
         uploader = self._html_search_regex(
-            r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
+            r'by:\s*<a [^>]*>(.+?)</a>',
+            webpage, 'uploader', fatal=False)
         uploader_id = self._html_search_regex(
-            r'by:\s*<a href="/Profile\.aspx\?.*?UserId=(\d+).*?"', webpage, 'uploader id', fatal=False)
-        upload_date = self._html_search_regex(r'</a> on (.+?) at \d+:\d+', webpage, 'upload date', fatal=False)
-        if upload_date:
-            upload_date = unified_strdate(upload_date)
-        
-        view_count = self._html_search_regex(
-            r'<div id="viewsCounter"><span>([^<]+)</span> views</div>', webpage, 'view count', fatal=False)
-        if view_count:
-            view_count = str_to_int(view_count)
-        comment_count = int_or_none(self._html_search_regex(
-            r'<span id="spCommentCount">\s*(\d+)</span> Comments</div>', webpage, 'comment count', fatal=False))
+            r'by:\s*<a href="/(?:user/viewProfile|Profile\.aspx)\?.*?UserId=(\d+).*?"',
+            webpage, 'uploader id', fatal=False)
+        upload_date = unified_strdate(self._html_search_regex(
+            r'</a> on (.+?) at \d+:\d+',
+            webpage, 'upload date', fatal=False))
+
+        view_count = str_to_int(self._html_search_regex(
+            r'<div id="viewsCounter"><span>([\d,\.]+)</span> views</div>',
+            webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._html_search_regex(
+            r'<span\s+id="spCommentCount"[^>]*>([\d,\.]+)</span>',
+            webpage, 'comment count', fatal=False))
 
-        video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
-        if webpage.find('flashvars\.encrypted = "true"') != -1:
-            password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, 'password').replace('+', ' ')
-            video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
+        videos = re.findall(
+            r'playerData\.cdnPath([0-9]{3,})\s*=\s*(?:encodeURIComponent\()?["\']([^"\']+)["\']', webpage)
+        heights = [int(video[0]) for video in videos]
+        video_urls = list(map(compat_urllib_parse_unquote, [video[1] for video in videos]))
+        if webpage.find(r'flashvars\.encrypted = "true"') != -1:
+            password = self._search_regex(
+                r'flashvars\.video_title = "([^"]+)',
+                webpage, 'password').replace('+', ' ')
+            video_urls = list(map(
+                lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'),
+                video_urls))
 
         formats = []
-        for video_url in video_urls:
+        for height, video_url in zip(heights, video_urls):
             path = compat_urllib_parse_urlparse(video_url).path
-            format = path.split('/')[4].split('_')[:2]
-            resolution, bitrate_str = format
-            format = "-".join(format)
-            height = int(resolution.rstrip('Pp'))
-            tbr = int(bitrate_str.rstrip('Kk'))
+            m = re.search(r'/(?P<height>\d+)[pP]_(?P<tbr>\d+)[kK]', path)
+            if m:
+                tbr = int(m.group('tbr'))
+                height = int(m.group('height'))
+            else:
+                tbr = None
             formats.append({
                 'url': video_url,
-                'resolution': resolution,
-                'format': format,
-                'tbr': tbr,
+                'format_id': '%dp' % height,
                 'height': height,
-                'format_id': format,
+                'tbr': tbr,
             })
         self._sort_formats(formats)