[pornflip] Add new extractor (#523)

Authored-by: mzbaulhaque
This commit is contained in:
mzbaulhaque 2021-07-20 00:16:21 +06:00 committed by GitHub
parent fe93e2c4cf
commit 8d9b902243
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 83 additions and 0 deletions

View file

@ -1015,6 +1015,7 @@
from .popcorntv import PopcornTVIE from .popcorntv import PopcornTVIE
from .porn91 import Porn91IE from .porn91 import Porn91IE
from .porncom import PornComIE from .porncom import PornComIE
from .pornflip import PornFlipIE
from .pornhd import PornHdIE from .pornhd import PornHdIE
from .pornhub import ( from .pornhub import (
PornHubIE, PornHubIE,

View file

@ -0,0 +1,82 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_duration,
parse_iso8601
)
class PornFlipIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:(embed|sv|v)/)?(?P<id>[^/]+)'
_TESTS = [
{
'url': 'https://www.pornflip.com/dzv9Mtw1qj2/sv/brazzers-double-dare-two-couples-fucked-jenna-reid-maya-bijou',
'info_dict': {
'id': 'dzv9Mtw1qj2',
'ext': 'mp4',
'title': 'Brazzers - Double Dare Two couples fucked Jenna Reid Maya Bijou',
'description': 'md5:d2b69e6cc743c5fd158e162aa7f05821',
'duration': 476,
'like_count': int,
'dislike_count': int,
'view_count': int,
'timestamp': 1617846819,
'upload_date': '20210408',
'uploader': 'Brazzers',
'age_limit': 18,
},
'params': {
'format': 'bestvideo',
'skip_download': True,
},
},
{
'url': 'https://www.pornflip.com/v/IrJEC40i21L',
'only_matching': True,
},
{
'url': 'https://www.pornflip.com/Z3jzbChC5-P/sexintaxi-e-sereyna-gomez-czech-naked-couple',
'only_matching': True,
},
{
'url': 'https://www.pornflip.com/embed/bLcDFxnrZnU',
'only_matching': True,
},
]
_HOST = 'www.pornflip.com'
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'https://{}/sv/{}'.format(self._HOST, video_id), video_id, headers={'host': self._HOST})
description = self._html_search_regex(r'&p\[summary\]=(.*?)\s*&p', webpage, 'description', fatal=False)
duration = self._search_regex(r'"duration":\s+"([^"]+)",', webpage, 'duration', fatal=False)
view_count = self._search_regex(r'"interactionCount":\s+"([^"]+)"', webpage, 'view_count', fatal=False)
title = self._html_search_regex(r'id="mediaPlayerTitleLink"[^>]*>(.+)</a>', webpage, 'title', fatal=False)
uploader = self._html_search_regex(r'class="title-chanel"[^>]*>[^<]*<a[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
upload_date = self._search_regex(r'"uploadDate":\s+"([^"]+)",', webpage, 'upload_date', fatal=False)
likes = self._html_search_regex(
r'class="btn btn-up-rating[^>]*>[^<]*<i[^>]*>[^<]*</i>[^>]*<span[^>]*>[^0-9]*([0-9]+)[^<0-9]*<', webpage, 'like_count', fatal=False)
dislikes = self._html_search_regex(
r'class="btn btn-down-rating[^>]*>[^<]*<i[^>]*>[^<]*</i>[^>]*<span[^>]*>[^0-9]*([0-9]+)[^<0-9]*<', webpage, 'dislike_count', fatal=False)
mpd_url = self._search_regex(r'"([^"]+userscontent.net/dash/[0-9]+/manifest.mpd[^"]*)"', webpage, 'mpd_url').replace('&amp;', '&')
formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash')
self._sort_formats(formats)
return {
'age_limit': 18,
'description': description,
'dislike_count': int_or_none(dislikes),
'duration': parse_duration(duration),
'formats': formats,
'id': video_id,
'like_count': int_or_none(likes),
'timestamp': parse_iso8601(upload_date),
'thumbnail': self._og_search_thumbnail(webpage),
'title': title,
'uploader': uploader,
'view_count': int_or_none(view_count),
}