R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[SpankBangPlaylistIE] change single video regex, used urljoin, eliminate duplicate video capture, playlist title is no longer fatal, used _match_id

Browse Source
This commit is contained in:
JChris246 2019-02-05 19:25:02 -04:00
parent 1ec0696196
commit 1a7f6314b6
1 changed files with 20 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
youtube_dl/extractor/spankbang.py
View File

@ -8,11 +8,12 @@ from ..utils import (
parse_duration, parse_duration,
parse_resolution, parse_resolution,
str_to_int, str_to_int,
urljoin,
) )
class SpankBangIE(InfoExtractor): class SpankBangIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z-]+)/(?:video|playlist)' _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
_TESTS = [{ _TESTS = [{
'url': 'http://spankbang.com/3vvn/video/fantasy+solo', 'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
'md5': '1cc433e1d6aa14bc376535b8679302f7', 'md5': '1cc433e1d6aa14bc376535b8679302f7',
@ -107,21 +108,27 @@ class SpankBangPlaylistIE(InfoExtractor):
'playlist_mincount': 2, 'playlist_mincount': 2,
} }
def _extract_entries(self, webpage): def _extract_entries(self, webpage, id):
return [ video_items = re.findall(r'<div[^>]+class=[\'"].*?video-item[^>]*>\s*(.+?)>', webpage)
self.url_result(
'http://www.%s/%s' % ('spankbang.com', video_url), entries = []
SpankBangIE.ie_key()) if video_items:
for video_url in re.findall( for div in video_items:
r'href="/?([\da-z-]+/playlist/[^"]+)', webpage) page_url = self._search_regex(
] r'href="/?(' + id + '-[\da-z]+/playlist/[^"]+)', div, 'page url', default=None)
if page_url:
page = self._download_webpage(urljoin('http://spankbang.com', page_url), id)
canonical_url = self._search_regex(
r'link rel="canonical" href="(.+?)"', page, 'canonical_url')
entries.append(self.url_result(canonical_url, SpankBangIE.ie_key()))
return entries
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) playlist_id = self._match_id(url)
playlist_id = mobj.group('id')
webpage = self._download_webpage(url, playlist_id) webpage = self._download_webpage(url, playlist_id)
entries = self._extract_entries(webpage) entries = self._extract_entries(webpage, playlist_id)
title = self._search_regex(r'<h1>(.+)</h1>', webpage, 'playlist_title') title = self._search_regex(r'<h1>(.+)</h1>', webpage, 'playlist_title', fatal=False)
return self.playlist_result(entries, playlist_id, title) return self.playlist_result(entries, playlist_id, title)