youtube-dl

commit 3fde134791fa920c98a99610c2200a6b3572cca0
parent 536b94e56fdf0fd2dd1c6d6d92112866949505c4
Author: Sergey M․ <dstftw@gmail.com>
Date:   Sat,  4 Apr 2015 19:14:01 +0600

Merge branch 'Roman2K-pornovoisines'

Diffstat:
M
test/test_utils.py
 | 
1
+
M
youtube_dl/extractor/__init__.py
 | 
1
+
A
youtube_dl/extractor/pornovoisines.py
 | 
96
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
M
youtube_dl/utils.py
 | 
5
++++-

4 files changed, 102 insertions(+), 1 deletion(-)
diff --git a/test/test_utils.py b/test/test_utils.py
@@ -227,6 +227,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(
             unified_strdate('2/2/2015 6:47:40 PM', day_first=False),
             '20150202')
+        self.assertEqual(unified_strdate('25-09-2014'), '20140925')
 
     def test_find_xpath_attr(self):
         testxml = '''<root>
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -388,6 +388,7 @@ from .pornhub import (
     PornHubPlaylistIE,
 )
 from .pornotube import PornotubeIE
+from .pornovoisines import PornoVoisinesIE
 from .pornoxo import PornoXOIE
 from .primesharetv import PrimeShareTVIE
 from .promptfile import PromptFileIE
diff --git a/youtube_dl/extractor/pornovoisines.py b/youtube_dl/extractor/pornovoisines.py
@@ -0,0 +1,96 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import random
+
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    float_or_none,
+    unified_strdate,
+)
+
+
+class PornoVoisinesIE(InfoExtractor):
+    _VALID_URL = r'http://(?:www\.)?pornovoisines\.com/showvideo/(?P<id>\d+)/(?P<display_id>[^/]+)'
+
+    _VIDEO_URL_TEMPLATE = 'http://stream%d.pornovoisines.com' \
+        '/static/media/video/transcoded/%s-640x360-1000-trscded.mp4'
+
+    _SERVER_NUMBERS = (1, 2)
+
+    _TEST = {
+        'url': 'http://www.pornovoisines.com/showvideo/1285/recherche-appartement/',
+        'md5': '5ac670803bc12e9e7f9f662ce64cf1d1',
+        'info_dict': {
+            'id': '1285',
+            'display_id': 'recherche-appartement',
+            'ext': 'mp4',
+            'title': 'Recherche appartement',
+            'description': 'md5:819ea0b785e2a04667a1a01cdc89594e',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'upload_date': '20140925',
+            'duration': 120,
+            'view_count': int,
+            'average_rating': float,
+            'categories': ['Débutante', 'Scénario', 'Sodomie'],
+            'age_limit': 18,
+        }
+    }
+
+    @classmethod
+    def build_video_url(cls, num):
+        return cls._VIDEO_URL_TEMPLATE % (random.choice(cls._SERVER_NUMBERS), num)
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        display_id = mobj.group('display_id')
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self.build_video_url(video_id)
+
+        title = self._html_search_regex(
+            r'<h1>(.+?)</h1>', webpage, 'title', flags=re.DOTALL)
+        description = self._html_search_regex(
+            r'<article id="descriptif">(.+?)</article>',
+            webpage, "description", fatal=False, flags=re.DOTALL)
+
+        thumbnail = self._search_regex(
+            r'<div id="mediaspace%s">\s*<img src="/?([^"]+)"' % video_id,
+            webpage, 'thumbnail', fatal=False)
+        if thumbnail:
+            thumbnail = 'http://www.pornovoisines.com/%s' % thumbnail
+
+        upload_date = unified_strdate(self._search_regex(
+            r'Publié le ([\d-]+)', webpage, 'upload date', fatal=False))
+        duration = int_or_none(self._search_regex(
+            'Durée (\d+)', webpage, 'duration', fatal=False))
+        view_count = int_or_none(self._search_regex(
+            r'(\d+) vues', webpage, 'view count', fatal=False))
+        average_rating = self._search_regex(
+            r'Note : (\d+,\d+)', webpage, 'average rating', fatal=False)
+        if average_rating:
+            average_rating = float_or_none(average_rating.replace(',', '.'))
+
+        categories = self._html_search_meta(
+            'keywords', webpage, 'categories', fatal=False)
+        if categories:
+            categories = [category.strip() for category in categories.split(',')]
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            'url': video_url,
+            'title': title,
+            'description': description,
+            'thumbnail': thumbnail,
+            'upload_date': upload_date,
+            'duration': duration,
+            'view_count': view_count,
+            'average_rating': average_rating,
+            'categories': categories,
+            'age_limit': 18,
+        }
diff --git a/youtube_dl/utils.py b/youtube_dl/utils.py
@@ -730,7 +730,8 @@ def unified_strdate(date_str, day_first=True):
     # Replace commas
     date_str = date_str.replace(',', ' ')
     # %z (UTC offset) is only supported in python>=3.2
-    date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
+    if not re.match(r'^[0-9]{1,2}-[0-9]{1,2}-[0-9]{4}$', date_str):
+        date_str = re.sub(r' ?(\+|-)[0-9]{2}:?[0-9]{2}$', '', date_str)
     # Remove AM/PM + timezone
     date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
 
@@ -759,6 +760,7 @@ def unified_strdate(date_str, day_first=True):
     ]
     if day_first:
         format_expressions.extend([
+            '%d-%m-%Y',
             '%d.%m.%Y',
             '%d/%m/%Y',
             '%d/%m/%y',
@@ -766,6 +768,7 @@ def unified_strdate(date_str, day_first=True):
         ])
     else:
         format_expressions.extend([
+            '%m-%d-%Y',
             '%m.%d.%Y',
             '%m/%d/%Y',
             '%m/%d/%y',