1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-27 19:04:32 +01:00
youtube-dl/youtube_dl/extractor/zaq1.py

102 lines
3.2 KiB
Python
Raw Normal View History

2017-04-09 12:02:44 +02:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_timestamp,
2017-04-09 12:02:44 +02:00
)
class Zaq1IE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?zaq1\.pl/video/(?P<id>[^/?#&]+)'
2017-04-09 12:02:44 +02:00
_TESTS = [{
'url': 'http://zaq1.pl/video/xev0e',
'md5': '24a5eb3f052e604ae597c4d0d19b351e',
'info_dict': {
'id': 'xev0e',
'title': 'DJ NA WESELE. TANIEC Z FIGURAMI.węgrów/sokołów podlaski/siedlce/mińsk mazowiecki/warszawa',
'description': 'www.facebook.com/weseledjKontakt: 728 448 199 / 505 419 147',
2017-04-09 12:02:44 +02:00
'ext': 'mp4',
'duration': 511,
'timestamp': 1490896361,
2017-04-09 12:02:44 +02:00
'uploader': 'Anonim',
'upload_date': '20170330',
'view_count': int,
2017-04-09 12:02:44 +02:00
}
}, {
# malformed JSON-LD
'url': 'http://zaq1.pl/video/x81vn',
2017-04-09 12:02:44 +02:00
'info_dict': {
'id': 'x81vn',
'title': 'SEKRETNE ŻYCIE WALTERA MITTY',
2017-04-09 12:02:44 +02:00
'ext': 'mp4',
'duration': 6234,
'timestamp': 1493494860,
2017-04-09 12:02:44 +02:00
'uploader': 'Anonim',
'upload_date': '20170429',
'view_count': int,
},
'params': {
'skip_download': True,
},
'expected_warnings': ['Failed to parse JSON'],
2017-04-09 12:02:44 +02:00
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'data-video-url=(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'video url', group='url')
info = self._search_json_ld(webpage, video_id, fatal=False)
def extract_data(field, name, fatal=False):
return self._search_regex(
r'data-%s=(["\'])(?P<field>(?:(?!\1).)+)\1' % field,
webpage, field, fatal=fatal, group='field')
if not info.get('title'):
info['title'] = extract_data('file-name', 'title', fatal=True)
if not info.get('duration'):
info['duration'] = int_or_none(extract_data('duration', 'duration'))
2017-04-09 12:02:44 +02:00
if not info.get('thumbnail'):
info['thumbnail'] = extract_data('photo-url', 'thumbnail')
2017-04-09 12:02:44 +02:00
if not info.get('timestamp'):
info['timestamp'] = unified_timestamp(self._html_search_meta(
'uploadDate', webpage, 'timestamp'))
2017-04-09 12:02:44 +02:00
if not info.get('interactionCount'):
info['view_count'] = int_or_none(self._html_search_meta(
'interactionCount', webpage, 'view count'))
2017-04-09 12:02:44 +02:00
uploader = self._html_search_regex(
r'Wideo dodał:\s*<a[^>]*>([^<]+)</a>', webpage, 'uploader',
fatal=False)
width = int_or_none(self._html_search_meta(
'width', webpage, fatal=False))
height = int_or_none(self._html_search_meta(
'height', webpage, fatal=False))
info.update({
2017-04-09 12:02:44 +02:00
'id': video_id,
'formats': [{
'url': video_url,
'width': width,
'height': height,
'http_headers': {
'Referer': url,
},
2017-04-09 12:02:44 +02:00
}],
'uploader': uploader,
})
return info