X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/575f75429e2e479957d006a26940f4a5a51347ce..39393b81acfaf4045fb7f20454a0226f0dc9142e:/youtube_dl/extractor/motherless.py
diff --git a/youtube_dl/extractor/motherless.py b/youtube_dl/extractor/motherless.py
index 6fe3b60..b1615b4 100644
--- a/youtube_dl/extractor/motherless.py
+++ b/youtube_dl/extractor/motherless.py
@@ -4,8 +4,11 @@ import datetime
import re
from .common import InfoExtractor
+from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
+ InAdvancePagedList,
+ orderedSet,
str_to_int,
unified_strdate,
)
@@ -23,7 +26,7 @@ class MotherlessIE(InfoExtractor):
'categories': ['Gaming', 'anal', 'reluctant', 'rough', 'Wife'],
'upload_date': '20100913',
'uploader_id': 'famouslyfuckedup',
- 'thumbnail': r're:http://.*\.jpg',
+ 'thumbnail': r're:https?://.*\.jpg',
'age_limit': 18,
}
}, {
@@ -37,7 +40,7 @@ class MotherlessIE(InfoExtractor):
'game', 'hairy'],
'upload_date': '20140622',
'uploader_id': 'Sulivana7x',
- 'thumbnail': r're:http://.*\.jpg',
+ 'thumbnail': r're:https?://.*\.jpg',
'age_limit': 18,
},
'skip': '404',
@@ -51,7 +54,7 @@ class MotherlessIE(InfoExtractor):
'categories': ['superheroine heroine superher'],
'upload_date': '20140827',
'uploader_id': 'shade0230',
- 'thumbnail': r're:http://.*\.jpg',
+ 'thumbnail': r're:https?://.*\.jpg',
'age_limit': 18,
}
}, {
@@ -73,19 +76,24 @@ class MotherlessIE(InfoExtractor):
raise ExtractorError('Video %s is for friends only' % video_id, expected=True)
title = self._html_search_regex(
- r'id="view-upload-title">\s+([^<]+)<', webpage, 'title')
- video_url = self._html_search_regex(
- r'setup\(\{\s+"file".+: "([^"]+)",', webpage, 'video URL')
+ (r'(?s)
]+\bclass=["\']media-meta-title[^>]+>(.+?)
',
+ r'id="view-upload-title">\s+([^<]+)<'), webpage, 'title')
+ video_url = (self._html_search_regex(
+ (r'setup\(\{\s*["\']file["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1',
+ r'fileurl\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'),
+ webpage, 'video URL', default=None, group='url')
+ or 'http://cdn4.videos.motherlessmedia.com/videos/%s.mp4?fs=opencloud' % video_id)
age_limit = self._rta_search(webpage)
view_count = str_to_int(self._html_search_regex(
- r'Views\s+([^<]+)<',
+ (r'>(\d+)\s+Views<', r'Views\s+([^<]+)<'),
webpage, 'view count', fatal=False))
like_count = str_to_int(self._html_search_regex(
- r'Favorited\s+([^<]+)<',
+ (r'>(\d+)\s+Favorites<', r'Favorited\s+([^<]+)<'),
webpage, 'like count', fatal=False))
upload_date = self._html_search_regex(
- r'Uploaded\s+([^<]+)<', webpage, 'upload date')
+ (r'class=["\']count[^>]+>(\d+\s+[a-zA-Z]{3}\s+\d{4})<',
+ r'Uploaded\s+([^<]+)<'), webpage, 'upload date')
if 'Ago' in upload_date:
days = int(re.search(r'([0-9]+)', upload_date).group(1))
upload_date = (datetime.datetime.now() - datetime.timedelta(days=days)).strftime('%Y%m%d')
@@ -114,3 +122,86 @@ class MotherlessIE(InfoExtractor):
'age_limit': age_limit,
'url': video_url,
}
+
+
+class MotherlessGroupIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?motherless\.com/gv?/(?P[a-z0-9_]+)'
+ _TESTS = [{
+ 'url': 'http://motherless.com/g/movie_scenes',
+ 'info_dict': {
+ 'id': 'movie_scenes',
+ 'title': 'Movie Scenes',
+ 'description': 'Hot and sexy scenes from "regular" movies... '
+ 'Beautiful actresses fully nude... A looot of '
+ 'skin! :)Enjoy!',
+ },
+ 'playlist_mincount': 662,
+ }, {
+ 'url': 'http://motherless.com/gv/sex_must_be_funny',
+ 'info_dict': {
+ 'id': 'sex_must_be_funny',
+ 'title': 'Sex must be funny',
+ 'description': 'Sex can be funny. Wide smiles,laugh, games, fun of '
+ 'any kind!'
+ },
+ 'playlist_mincount': 9,
+ }]
+
+ @classmethod
+ def suitable(cls, url):
+ return (False if MotherlessIE.suitable(url)
+ else super(MotherlessGroupIE, cls).suitable(url))
+
+ def _extract_entries(self, webpage, base):
+ entries = []
+ for mobj in re.finditer(
+ r'href="(?P/[^"]+)"[^>]*>(?:\s*]+alt="[^-]+-\s(?P[^"]+)")?',
+ webpage):
+ video_url = compat_urlparse.urljoin(base, mobj.group('href'))
+ if not MotherlessIE.suitable(video_url):
+ continue
+ video_id = MotherlessIE._match_id(video_url)
+ title = mobj.group('title')
+ entries.append(self.url_result(
+ video_url, ie=MotherlessIE.ie_key(), video_id=video_id,
+ video_title=title))
+ # Alternative fallback
+ if not entries:
+ entries = [
+ self.url_result(
+ compat_urlparse.urljoin(base, '/' + entry_id),
+ ie=MotherlessIE.ie_key(), video_id=entry_id)
+ for entry_id in orderedSet(re.findall(
+ r'data-codename=["\']([A-Z0-9]+)', webpage))]
+ return entries
+
+ def _real_extract(self, url):
+ group_id = self._match_id(url)
+ page_url = compat_urlparse.urljoin(url, '/gv/%s' % group_id)
+ webpage = self._download_webpage(page_url, group_id)
+ title = self._search_regex(
+ r'([\w\s]+\w)\s+-', webpage, 'title', fatal=False)
+ description = self._html_search_meta(
+ 'description', webpage, fatal=False)
+ page_count = self._int(self._search_regex(
+ r'(\d+)(?:a|span)><(?:a|span)[^>]+>\s*NEXT',
+ webpage, 'page_count'), 'page_count')
+ PAGE_SIZE = 80
+
+ def _get_page(idx):
+ webpage = self._download_webpage(
+ page_url, group_id, query={'page': idx + 1},
+ note='Downloading page %d/%d' % (idx + 1, page_count)
+ )
+ for entry in self._extract_entries(webpage, url):
+ yield entry
+
+ playlist = InAdvancePagedList(_get_page, page_count, PAGE_SIZE)
+
+ return {
+ '_type': 'playlist',
+ 'id': group_id,
+ 'title': title,
+ 'description': description,
+ 'entries': playlist
+ }