Imported Upstream version 2014.07.15

[youtubedl] / youtube_dl / extractor / youporn.py

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index bd0f2cae0298dec0d78f812153976ec6a8434bb0..d456c4da522d689ac7bcbd33c5f8a3b1204c3b00 100644 (file)
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -1,5 +1,7 @@
+from __future__ import unicode_literals
+
+

 import json
 import json

-import os

 import re
 import sys
 
 import re
 import sys
 


@@ -16,25 +18,27 @@ from ..aes import (
     aes_decrypt_text
 )
 
     aes_decrypt_text
 )
 

+

 class YouPornIE(InfoExtractor):
 class YouPornIE(InfoExtractor):

-    _VALID_URL = r'^(?:https?://)?(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
+    _VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'

     _TEST = {
     _TEST = {

-        u'url': u'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
-        u'file': u'505835.mp4',
-        u'md5': u'71ec5fcfddacf80f495efa8b6a8d9a89',
-        u'info_dict': {
-            u"upload_date": u"20101221", 
-            u"description": u"Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?", 
-            u"uploader": u"Ask Dan And Jennifer", 
-            u"title": u"Sex Ed: Is It Safe To Masturbate Daily?",
-            u"age_limit": 18,
+        'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
+        'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
+        'info_dict': {
+            'id': '505835',
+            'ext': 'mp4',
+            'upload_date': '20101221',
+            'description': 'Love & Sex Answers: http://bit.ly/DanAndJenn -- Is It Unhealthy To Masturbate Daily?',
+            'uploader': 'Ask Dan And Jennifer',
+            'title': 'Sex Ed: Is It Safe To Masturbate Daily?',
+            'age_limit': 18,

         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')
         }
     }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('videoid')

-        url = 'http://www.' + mobj.group('url')
+        url = mobj.group('proto') + 'www.' + mobj.group('url')

 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')


@@ -42,7 +46,7 @@ class YouPornIE(InfoExtractor):
         age_limit = self._rta_search(webpage)
 
         # Get JSON parameters
         age_limit = self._rta_search(webpage)
 
         # Get JSON parameters

-        json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
+        json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, 'JSON parameters')

         try:
             params = json.loads(json_params)
         except:
         try:
             params = json.loads(json_params)
         except:


@@ -61,7 +65,7 @@ class YouPornIE(InfoExtractor):
         # Get all of the links from the page
         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,
         # Get all of the links from the page
         DOWNLOAD_LIST_RE = r'(?s)<ul class="downloadList">(?P<download_list>.*?)</ul>'
         download_list_html = self._search_regex(DOWNLOAD_LIST_RE,

-            webpage, u'download list').strip()
+            webpage, 'download list').strip()

         LINK_RE = r'<a href="([^"]+)">'
         links = re.findall(LINK_RE, download_list_html)
 
         LINK_RE = r'<a href="([^"]+)">'
         links = re.findall(LINK_RE, download_list_html)
 


@@ -71,38 +75,36 @@ class YouPornIE(InfoExtractor):
             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
             links.append(link)
         
             link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
             links.append(link)
         

-        if not links:
-            raise ExtractorError(u'ERROR: no known formats available for video')
-

         formats = []
         for link in links:
         formats = []
         for link in links:

-

             # A link looks like this:
             # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
             # A path looks like this:
             # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
             video_url = unescapeHTML(link)
             path = compat_urllib_parse_urlparse(video_url).path
             # A link looks like this:
             # http://cdn1.download.youporn.phncdn.com/201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4?nvb=20121113051249&nva=20121114051249&ir=1200&sr=1200&hash=014b882080310e95fb6a0
             # A path looks like this:
             # /201210/31/8004515/480p_370k_8004515/YouPorn%20-%20Nubile%20Films%20The%20Pillow%20Fight.mp4
             video_url = unescapeHTML(link)
             path = compat_urllib_parse_urlparse(video_url).path

-            extension = os.path.splitext(path)[1][1:]
-            format = path.split('/')[4].split('_')[:2]
+            format_parts = path.split('/')[4].split('_')[:2]
+
+            dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]

 
 

-            # size = format[0]
-            # bitrate = format[1]
-            format = "-".join(format)
-            # title = u'%s-%s-%s' % (video_title, size, bitrate)
+            resolution = format_parts[0]
+            height = int(resolution[:-len('p')])
+            bitrate = int(format_parts[1][:-len('k')])
+            format = '-'.join(format_parts) + '-' + dn

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

-                'ext': extension,

                 'format': format,
                 'format_id': format,
                 'format': format,
                 'format_id': format,

+                'height': height,
+                'tbr': bitrate,
+                'resolution': resolution,

             })
 
             })
 

-        # Sort and remove doubles
-        formats.sort(key=lambda format: list(map(lambda s: s.zfill(6), format['format'].split('-'))))
-        for i in range(len(formats)-1,0,-1):
-            if formats[i]['format_id'] == formats[i-1]['format_id']:
-                del formats[i]
+        self._sort_formats(formats)
+
+        if not formats:
+            raise ExtractorError(u'ERROR: no known formats available for video')

         
         return {
             'id': video_id,
         
         return {
             'id': video_id,