d/rules: Run offline tests.

[youtubedl] / youtube_dl / extractor / pornhd.py

diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index 8df12eec0d44c371d99b536b55694cfd2211f9d0..27d65d4b9cdcf1e068b0d6971502eaa0caccf895 100644 (file)
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -4,9 +4,11 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
 
 from .common import InfoExtractor
 from ..utils import (

+    determine_ext,

     ExtractorError,
     int_or_none,
     js_to_json,
     ExtractorError,
     int_or_none,
     js_to_json,

+    urljoin,

 )
 
 
 )
 
 


@@ -14,15 +16,16 @@ class PornHdIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
     _TESTS = [{
         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
     _VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P<id>\d+)(?:/(?P<display_id>.+))?'
     _TESTS = [{
         'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',

-        'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
+        'md5': '87f1540746c1d32ec7a2305c12b96b25',

         'info_dict': {
             'id': '9864',
             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
             'ext': 'mp4',
             'title': 'Restroom selfie masturbation',
             'description': 'md5:3748420395e03e31ac96857a8f125b2b',
         'info_dict': {
             'id': '9864',
             'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
             'ext': 'mp4',
             'title': 'Restroom selfie masturbation',
             'description': 'md5:3748420395e03e31ac96857a8f125b2b',

-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',

             'view_count': int,
             'view_count': int,

+            'like_count': int,

             'age_limit': 18,
         }
     }, {
             'age_limit': 18,
         }
     }, {


@@ -35,8 +38,9 @@ class PornHdIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Sierra loves doing laundry',
             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
             'ext': 'mp4',
             'title': 'Sierra loves doing laundry',
             'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',

-            'thumbnail': 're:^https?://.*\.jpg',
+            'thumbnail': r're:^https?://.*\.jpg',

             'view_count': int,
             'view_count': int,

+            'like_count': int,

             'age_limit': 18,
         },
         'skip': 'Not available anymore',
             'age_limit': 18,
         },
         'skip': 'Not available anymore',


@@ -54,7 +58,7 @@ class PornHdIE(InfoExtractor):
              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
 
         sources = self._parse_json(js_to_json(self._search_regex(
              r'<title>(.+?) - .*?[Pp]ornHD.*?</title>'], webpage, 'title')
 
         sources = self._parse_json(js_to_json(self._search_regex(

-            r"(?s)'sources'\s*:\s*(\{.+?\})\s*\}[;,)]",
+            r"(?s)sources'?\s*[:=]\s*(\{.+?\})",

             webpage, 'sources', default='{}')), video_id)
 
         if not sources:
             webpage, 'sources', default='{}')), video_id)
 
         if not sources:


@@ -65,12 +69,14 @@ class PornHdIE(InfoExtractor):
 
         formats = []
         for format_id, video_url in sources.items():
 
         formats = []
         for format_id, video_url in sources.items():

+            video_url = urljoin(url, video_url)

             if not video_url:
                 continue
             height = int_or_none(self._search_regex(
                 r'^(\d+)[pP]', format_id, 'height', default=None))
             formats.append({
                 'url': video_url,
             if not video_url:
                 continue
             height = int_or_none(self._search_regex(
                 r'^(\d+)[pP]', format_id, 'height', default=None))
             formats.append({
                 'url': video_url,

+                'ext': determine_ext(video_url, 'mp4'),

                 'format_id': format_id,
                 'height': height,
             })
                 'format_id': format_id,
                 'height': height,
             })


@@ -82,7 +88,13 @@ class PornHdIE(InfoExtractor):
         view_count = int_or_none(self._html_search_regex(
             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
         thumbnail = self._search_regex(
         view_count = int_or_none(self._html_search_regex(
             r'(\d+) views\s*<', webpage, 'view count', fatal=False))
         thumbnail = self._search_regex(

-            r"'poster'\s*:\s*'([^']+)'", webpage, 'thumbnail', fatal=False)
+            r"poster'?\s*:\s*([\"'])(?P<url>(?:(?!\1).)+)\1", webpage,
+            'thumbnail', fatal=False, group='url')
+
+        like_count = int_or_none(self._search_regex(
+            (r'(\d+)\s*</11[^>]+>(?:&nbsp;|\s)*\blikes',
+             r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
+            webpage, 'like count', fatal=False))

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


@@ -91,6 +103,7 @@ class PornHdIE(InfoExtractor):
             'description': description,
             'thumbnail': thumbnail,
             'view_count': view_count,
             'description': description,
             'thumbnail': thumbnail,
             'view_count': view_count,

+            'like_count': like_count,

             'formats': formats,
             'age_limit': 18,
         }
             'formats': formats,
             'age_limit': 18,
         }