Tidy up cleanup rule and keep lintian happy.

[youtubedl] / youtube_dl / extractor / spankwire.py

diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py
index 97f9c268a4531114912f9209c8a959d567add062..92a7120a3242e732ceb58f51b4391a5efbc569d8 100644 (file)
--- a/youtube_dl/extractor/spankwire.py
+++ b/youtube_dl/extractor/spankwire.py
@@ -1,74 +1,127 @@
-import os
+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_unquote,

     compat_urllib_parse_urlparse,
     compat_urllib_parse_urlparse,

-    compat_urllib_request,
-    compat_urllib_parse,
-    unescapeHTML,

 )
 )

-from ..aes import (
-    aes_decrypt_text
+from ..utils import (
+    sanitized_Request,
+    str_to_int,
+    unified_strdate,

 )
 )

+from ..aes import aes_decrypt_text
+

 
 class SpankwireIE(InfoExtractor):
 
 class SpankwireIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'
-    _TEST = {
-        u'url': u'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
-        u'file': u'103545.mp4',
-        u'md5': u'1b3f55e345500552dbc252a3e9c1af43',
-        u'info_dict': {
-            u"uploader": u"oreusz", 
-            u"title": u"Buckcherry`s X Rated Music Video Crazy Bitch",
-            u"description": u"Crazy Bitch X rated music video.",
-            u"age_limit": 18,
+    _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': {
+            'id': '103545',
+            'ext': 'mp4',
+            'title': 'Buckcherry`s X Rated Music Video Crazy Bitch',
+            'description': 'Crazy Bitch X rated music video.',
+            'uploader': 'oreusz',
+            'uploader_id': '124697',
+            '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)
 
     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)
 
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 

-        video_title = self._html_search_regex(r'<h1>([^<]+)', webpage, u'title')
-        video_uploader = self._html_search_regex(r'by:\s*<a [^>]*>(.+?)</a>', webpage, u'uploader', fatal=False)
-        thumbnail = self._html_search_regex(r'flashvars\.image_url = "([^"]+)', webpage, u'thumbnail', fatal=False)
-        description = self._html_search_regex(r'>\s*Description:</div>\s*<[^>]*>([^<]+)', webpage, u'description', fatal=False)
-        if len(description) == 0:
-            description = None
+        title = self._html_search_regex(
+            r'<h1>([^<]+)', webpage, 'title')
+        description = self._html_search_regex(
+            r'(?s)<div\s+id="descriptionContent">(.+?)</div>',
+            webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
+            webpage, 'thumbnail', fatal=False)

 
 

-        video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
+        uploader = self._html_search_regex(
+            r'by:\s*<a [^>]*>(.+?)</a>',
+            webpage, 'uploader', fatal=False)
+        uploader_id = self._html_search_regex(
+            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))
+
+        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('flashvars\.encrypted = "true"') != -1:
         if webpage.find('flashvars\.encrypted = "true"') != -1:

-            password = self._html_search_regex(r'flashvars\.video_title = "([^"]+)', webpage, u'password').replace('+', ' ')
-            video_urls = list(map(lambda s: aes_decrypt_text(s, password, 32).decode('utf-8'), video_urls))
+            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 = []
 
         formats = []

-        for video_url in video_urls:
+        for height, video_url in zip(heights, video_urls):

             path = compat_urllib_parse_urlparse(video_url).path
             path = compat_urllib_parse_urlparse(video_url).path

-            extension = os.path.splitext(path)[1][1:]
-            format = path.split('/')[4].split('_')[:2]
-            format = "-".join(format)
+            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,
             formats.append({
                 'url': video_url,

-                'ext': extension,
-                'format': format,
-                'format_id': format,
+                'format_id': '%dp' % height,
+                'height': height,
+                'tbr': tbr,

             })
             })

-        formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
+        self._sort_formats(formats)

 
         age_limit = self._rta_search(webpage)
 
         return {
             'id': video_id,
 
         age_limit = self._rta_search(webpage)
 
         return {
             'id': video_id,

-            'uploader': video_uploader,
-            'title': video_title,
-            'thumbnail': thumbnail,
+            'title': title,

             'description': description,
             'description': description,

+            'thumbnail': thumbnail,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
+            'upload_date': upload_date,
+            'view_count': view_count,
+            'comment_count': comment_count,

             'formats': formats,
             'age_limit': age_limit,
         }
             'formats': formats,
             'age_limit': age_limit,
         }