Merge tag 'upstream/2014.12.01'

[youtubedl] / youtube_dl / extractor / spankwire.py

diff --git a/youtube_dl/extractor/spankwire.py b/youtube_dl/extractor/spankwire.py
index 3362b3db85c65c97d8839d8707e36fecf8bc6646..94602e89e56549243ed38ecb107ef842cd8ebd46 100644 (file)
--- a/youtube_dl/extractor/spankwire.py
+++ b/youtube_dl/extractor/spankwire.py
@@ -1,6 +1,5 @@
 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import os

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


@@ -8,23 +7,26 @@ from ..utils import (
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,
     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse,

+    unified_strdate,
+    str_to_int,

 )
 )

-from ..aes import (
-    aes_decrypt_text
-)
+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]+)/?)'
+    _VALID_URL = r'https?://(?:www\.)?(?P<url>spankwire\.com/[^/]*/video(?P<videoid>[0-9]+)/?)'

     _TEST = {
         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',
     _TEST = {
         'url': 'http://www.spankwire.com/Buckcherry-s-X-Rated-Music-Video-Crazy-Bitch/video103545/',

-        'file': '103545.mp4',
-        'md5': '1b3f55e345500552dbc252a3e9c1af43',
+        'md5': '8bbfde12b101204b39e4b9fe7eb67095',

         'info_dict': {
         'info_dict': {

-            "uploader": "oreusz",
-            "title": "Buckcherry`s X Rated Music Video Crazy Bitch",
-            "description": "Crazy Bitch X rated music video.",
-            "age_limit": 18,
+            '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': '20070508',
+            'age_limit': 18,

         }
     }
 
         }
     }
 


@@ -37,32 +39,53 @@ class SpankwireIE(InfoExtractor):
         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, 'title')
-        video_uploader = self._html_search_regex(
-            r'by:\s*<a [^>]*>(.+?)</a>', webpage, 'uploader', fatal=False)
-        thumbnail = self._html_search_regex(
-            r'flashvars\.image_url = "([^"]+)', webpage, 'thumbnail', fatal=False)
+        title = self._html_search_regex(
+            r'<h1>([^<]+)', webpage, 'title')

         description = self._html_search_regex(
         description = self._html_search_regex(

-            r'<div\s+id="descriptionContent">([^<]+)<', webpage, 'description', fatal=False)
+            r'<div\s+id="descriptionContent">([^<]+)<',
+            webpage, 'description', fatal=False)
+        thumbnail = self._html_search_regex(
+            r'playerData\.screenShot\s*=\s*["\']([^"\']+)["\']',
+            webpage, 'thumbnail', fatal=False)
+
+        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="/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))

 
 

-        video_urls = list(map(compat_urllib_parse.unquote , re.findall(r'flashvars\.quality_[0-9]{3}p = "([^"]+)', webpage)))
+        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'Comments<span[^>]+>\s*\(([\d,\.]+)\)</span>',
+            webpage, 'comment count', fatal=False))
+
+        video_urls = list(map(
+            compat_urllib_parse.unquote,
+            re.findall(r'playerData\.cdnPath[0-9]{3,}\s*=\s*["\']([^"\']+)["\']', webpage)))

         if webpage.find('flashvars\.encrypted = "true"') != -1:
         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))
+            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))

 
         formats = []
         for video_url in video_urls:
             path = compat_urllib_parse_urlparse(video_url).path
 
         formats = []
         for video_url in video_urls:
             path = compat_urllib_parse_urlparse(video_url).path

-            extension = os.path.splitext(path)[1][1:]

             format = path.split('/')[4].split('_')[:2]
             resolution, bitrate_str = format
             format = "-".join(format)
             format = path.split('/')[4].split('_')[:2]
             resolution, bitrate_str = format
             format = "-".join(format)

-            height = int(resolution.rstrip('P'))
-            tbr = int(bitrate_str.rstrip('K'))
-
+            height = int(resolution.rstrip('Pp'))
+            tbr = int(bitrate_str.rstrip('Kk'))

             formats.append({
                 'url': video_url,
             formats.append({
                 'url': video_url,

-                'ext': extension,

                 'resolution': resolution,
                 'format': format,
                 'tbr': tbr,
                 'resolution': resolution,
                 'format': format,
                 'tbr': tbr,


@@ -75,10 +98,14 @@ class SpankwireIE(InfoExtractor):
 
         return {
             'id': video_id,
 
         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,
         }