debian/changelog: Annotate bugs to close.

[youtubedl] / youtube_dl / extractor / youporn.py

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 5d8b7db2cefe9175f37e3c1902c3288ef816ee49..4ba7c36db78fb457b63e05fe161a75b00383c78c 100644 (file)
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -1,50 +1,59 @@
+from __future__ import unicode_literals
+
+

 import json
 import json

-import os

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

-from ..utils import (
+from ..compat import (

     compat_urllib_parse_urlparse,
     compat_urllib_request,
     compat_urllib_parse_urlparse,
     compat_urllib_request,

-
+)
+from ..utils import (

     ExtractorError,
     unescapeHTML,
     unified_strdate,
 )
     ExtractorError,
     unescapeHTML,
     unified_strdate,
 )

+from ..aes import (
+    aes_decrypt_text
+)

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

-    _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+)'
-
-    def _print_formats(self, formats):
-        """Print all available formats"""
-        print(u'Available formats:')
-        print(u'ext\t\tformat')
-        print(u'---------------------------------')
-        for format in formats:
-            print(u'%s\t\t%s'  % (format['ext'], format['format']))
-
-    def _specific(self, req_format, formats):
-        for x in formats:
-            if x["format"] == req_format:
-                return x
-        return None
+    _VALID_URL = r'^(?P<proto>https?://)(?:www\.)?(?P<url>youporn\.com/watch/(?P<videoid>[0-9]+)/(?P<title>[^/]+))'
+    _TEST = {
+        'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
+        '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 = mobj.group('proto') + 'www.' + mobj.group('url')

 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)
 
         req = compat_urllib_request.Request(url)
         req.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(req, video_id)

+        age_limit = self._rta_search(webpage)

 
         # Get JSON parameters
 
         # Get JSON parameters

-        json_params = self._search_regex(r'var currentVideo = new Video\((.*)\);', webpage, u'JSON parameters')
+        json_params = self._search_regex(
+            [r'videoJa?son\s*=\s*({.+})',
+             r'var\s+currentVideo\s*=\s*new\s+Video\((.+?)\)[,;]'],
+            webpage, 'JSON parameters')

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

-        except:
-            raise ExtractorError(u'Invalid JSON')
+        except ValueError:
+            raise ExtractorError('Invalid JSON')

 
         self.report_extraction(video_id)
         try:
 
         self.report_extraction(video_id)
         try:


@@ -56,62 +65,57 @@ class YouPornIE(InfoExtractor):
         except KeyError:
             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
 
         except KeyError:
             raise ExtractorError('Missing JSON parameter: ' + sys.exc_info()[1])
 

-        # Get all of the formats available
+        # 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,
         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()
-
-        # Get all of the links from the page
-        LINK_RE = r'(?s)<a href="(?P<url>[^"]+)">'
+                                                webpage, 'download list').strip()
+        LINK_RE = r'<a href="([^"]+)">'

         links = re.findall(LINK_RE, download_list_html)
         links = re.findall(LINK_RE, download_list_html)

-        if(len(links) == 0):
-            raise ExtractorError(u'ERROR: no known formats available for video')

 
 

-        self.to_screen(u'Links found: %d' % len(links))
+        # Get all encrypted links
+        encrypted_links = re.findall(r'var encryptedQuality[0-9]{3}URL = \'([a-zA-Z0-9+/]+={0,2})\';', webpage)
+        for encrypted_link in encrypted_links:
+            link = aes_decrypt_text(encrypted_link, video_title, 32).decode('utf-8')
+            links.append(link)

 
         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
             # 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]
-            # size = format[0]
-            # bitrate = format[1]
-            format = "-".join( format )
-            # title = u'%s-%s-%s' % (video_title, size, bitrate)
+            video_url = unescapeHTML(link)
+            path = compat_urllib_parse_urlparse(video_url).path
+            format_parts = path.split('/')[4].split('_')[:2]
+
+            dn = compat_urllib_parse_urlparse(video_url).netloc.partition('.')[0]
+
+            resolution = format_parts[0]
+            height = int(resolution[:-len('p')])
+            bitrate = int(format_parts[1][:-len('k')])
+            format = '-'.join(format_parts) + '-' + dn

 
             formats.append({
 
             formats.append({

-                'id': video_id,

                 'url': video_url,
                 'url': video_url,

-                'uploader': video_uploader,
-                'upload_date': upload_date,
-                'title': video_title,
-                'ext': extension,

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

-                'thumbnail': thumbnail,
-                'description': video_description
+                'format_id': format,
+                'height': height,
+                'tbr': bitrate,
+                'resolution': resolution,

             })
 
             })
 

-        if self._downloader.params.get('listformats', None):
-            self._print_formats(formats)
-            return
-
-        req_format = self._downloader.params.get('format', None)
-        self.to_screen(u'Format: %s' % req_format)
-
-        if req_format is None or req_format == 'best':
-            return [formats[0]]
-        elif req_format == 'worst':
-            return [formats[-1]]
-        elif req_format in ('-1', 'all'):
-            return formats
-        else:
-            format = self._specific( req_format, formats )
-            if format is None:
-                raise ExtractorError(u'Requested format not available')
-            return [format]
+        self._sort_formats(formats)
+
+        if not formats:
+            raise ExtractorError('ERROR: no known formats available for video')
+
+        return {
+            'id': video_id,
+            'uploader': video_uploader,
+            'upload_date': upload_date,
+            'title': video_title,
+            'thumbnail': thumbnail,
+            'description': video_description,
+            'age_limit': age_limit,
+            'formats': formats,
+        }