[motherless] Add support for groups

This commit is contained in:
Martin Weinelt 2018-01-06 17:33:40 +01:00 committed by Sergey M
parent b7c74c0403
commit 45283afdec
2 changed files with 77 additions and 1 deletions

View File

@ -609,7 +609,10 @@
from .mojvideo import MojvideoIE from .mojvideo import MojvideoIE
from .moniker import MonikerIE from .moniker import MonikerIE
from .morningstar import MorningstarIE from .morningstar import MorningstarIE
from .motherless import MotherlessIE from .motherless import (
MotherlessIE,
MotherlessGroupIE
)
from .motorsport import MotorsportIE from .motorsport import MotorsportIE
from .movieclips import MovieClipsIE from .movieclips import MovieClipsIE
from .moviezine import MoviezineIE from .moviezine import MoviezineIE

View File

@ -4,8 +4,11 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import ( from ..utils import (
ExtractorError, ExtractorError,
InAdvancePagedList,
orderedSet,
str_to_int, str_to_int,
unified_strdate, unified_strdate,
) )
@ -114,3 +117,73 @@ def _real_extract(self, url):
'age_limit': age_limit, 'age_limit': age_limit,
'url': video_url, 'url': video_url,
} }
class MotherlessGroupIE(InfoExtractor):
_VALID_URL = 'https?://(?:www\.)?motherless\.com/gv?/(?P<id>[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):
return [
self.url_result(
compat_urlparse.urljoin(base, video_path),
MotherlessIE.ie_key(), video_title=title)
for video_path, title in orderedSet(re.findall(
r'href="/([^"]+)"[^>]+>\s+<img[^>]+alt="[^-]+-\s([^"]+)"',
webpage))
]
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'<title>([\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
}