yt-dlp/yt_dlp/extractor/pornovoisines.py

108 lines
3.9 KiB
Python
Raw Normal View History

2015-03-22 19:25:44 +00:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
2015-04-04 13:13:37 +00:00
from ..utils import (
int_or_none,
float_or_none,
unified_strdate,
)
2015-03-22 19:25:44 +00:00
class PornoVoisinesIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornovoisines\.com/videos/show/(?P<id>\d+)/(?P<display_id>[^/.]+)'
2015-03-22 19:25:44 +00:00
_TEST = {
'url': 'http://www.pornovoisines.com/videos/show/919/recherche-appartement.html',
'md5': '6f8aca6a058592ab49fe701c8ba8317b',
2015-03-22 19:25:44 +00:00
'info_dict': {
'id': '919',
2015-03-22 19:25:44 +00:00
'display_id': 'recherche-appartement',
'ext': 'mp4',
2015-04-04 13:13:37 +00:00
'title': 'Recherche appartement',
'description': 'md5:fe10cb92ae2dd3ed94bb4080d11ff493',
'thumbnail': r're:^https?://.*\.jpg$',
2015-03-22 19:25:44 +00:00
'upload_date': '20140925',
'duration': 120,
2015-04-04 13:13:37 +00:00
'view_count': int,
2015-03-22 19:25:44 +00:00
'average_rating': float,
'categories': ['Débutante', 'Débutantes', 'Scénario', 'Sodomie'],
2015-03-22 19:25:44 +00:00
'age_limit': 18,
'subtitles': {
'fr': [{
'ext': 'vtt',
}]
},
2015-03-22 19:25:44 +00:00
}
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
2015-04-04 13:13:37 +00:00
video_id = mobj.group('id')
display_id = mobj.group('display_id')
settings_url = self._download_json(
'http://www.pornovoisines.com/api/video/%s/getsettingsurl/' % video_id,
video_id, note='Getting settings URL')['video_settings_url']
settings = self._download_json(settings_url, video_id)['data']
formats = []
for kind, data in settings['variants'].items():
if kind == 'HLS':
formats.extend(self._extract_m3u8_formats(
data, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls'))
elif kind == 'MP4':
for item in data:
formats.append({
'url': item['url'],
'height': item.get('height'),
'bitrate': item.get('bitrate'),
})
self._sort_formats(formats)
2015-04-04 13:13:37 +00:00
webpage = self._download_webpage(url, video_id)
2015-04-04 13:13:37 +00:00
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
2015-04-04 13:13:37 +00:00
# The webpage has a bug - there's no space between "thumb" and src=
thumbnail = self._html_search_regex(
r'<img[^>]+class=([\'"])thumb\1[^>]*src=([\'"])(?P<url>[^"]+)\2',
webpage, 'thumbnail', fatal=False, group='url')
2015-04-04 13:13:37 +00:00
upload_date = unified_strdate(self._search_regex(
r'Le\s*<b>([\d/]+)', webpage, 'upload date', fatal=False))
duration = settings.get('main', {}).get('duration')
2015-04-04 13:13:37 +00:00
view_count = int_or_none(self._search_regex(
r'(\d+) vues', webpage, 'view count', fatal=False))
average_rating = self._search_regex(
r'Note\s*:\s*(\d+(?:,\d+)?)', webpage, 'average rating', fatal=False)
2015-04-04 13:13:37 +00:00
if average_rating:
average_rating = float_or_none(average_rating.replace(',', '.'))
categories = self._html_search_regex(
r'(?s)Catégories\s*:\s*<b>(.+?)</b>', webpage, 'categories', fatal=False)
2015-04-04 13:13:37 +00:00
if categories:
categories = [category.strip() for category in categories.split(',')]
2015-03-22 19:25:44 +00:00
subtitles = {'fr': [{
'url': subtitle,
} for subtitle in settings.get('main', {}).get('vtt_tracks', {}).values()]}
2015-03-22 19:25:44 +00:00
return {
2015-04-04 13:13:37 +00:00
'id': video_id,
2015-03-22 19:25:44 +00:00
'display_id': display_id,
'formats': formats,
2015-03-22 19:25:44 +00:00
'title': title,
'description': description,
'thumbnail': thumbnail,
2015-04-04 13:13:37 +00:00
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
2015-03-22 19:25:44 +00:00
'average_rating': average_rating,
2015-04-04 13:13:37 +00:00
'categories': categories,
2015-03-22 19:25:44 +00:00
'age_limit': 18,
'subtitles': subtitles,
2015-03-22 19:25:44 +00:00
}