1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-25 22:23:19 +01:00
yt-dlp/youtube_dl/extractor/presstv.py

75 lines
2.3 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2016-04-11 10:14:07 +02:00
import re
from .common import InfoExtractor
2016-04-11 10:14:07 +02:00
from ..utils import remove_start
class PressTVIE(InfoExtractor):
2016-04-11 10:14:07 +02:00
_VALID_URL = r'https?://(?:www\.)?presstv\.ir/[^/]+/(?P<y>\d+)/(?P<m>\d+)/(?P<d>\d+)/(?P<id>\d+)/(?P<display_id>[^/]+)?'
_TEST = {
'url': 'http://www.presstv.ir/Detail/2016/04/09/459911/Australian-sewerage-treatment-facility-/',
'md5': '5d7e3195a447cb13e9267e931d8dd5a5',
'info_dict': {
'id': '459911',
2016-04-11 10:14:07 +02:00
'display_id': 'Australian-sewerage-treatment-facility-',
'ext': 'mp4',
'title': 'Organic mattresses used to clean waste water',
'upload_date': '20160409',
2016-04-10 16:36:44 +02:00
'thumbnail': 're:^https?://.*\.jpg',
'description': 'md5:20002e654bbafb6908395a5c0cfcd125'
}
}
def _real_extract(self, url):
2016-04-11 10:14:07 +02:00
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
display_id = mobj.group('display_id') or video_id
webpage = self._download_webpage(url, display_id)
# extract video URL from webpage
2016-04-11 10:14:07 +02:00
video_url = self._hidden_inputs(webpage)['inpPlayback']
# build list of available formats
# specified in http://www.presstv.ir/Scripts/playback.js
base_url = 'http://192.99.219.222:82/presstv'
2016-04-10 16:36:44 +02:00
_formats = [
2016-04-11 10:14:07 +02:00
(180, '_low200.mp4'),
(360, '_low400.mp4'),
(720, '_low800.mp4'),
(1080, '.mp4')
]
2016-04-10 16:36:44 +02:00
2016-04-11 10:14:07 +02:00
formats = [{
'url': base_url + video_url[:-4] + extension,
'format_id': '%dp' % height,
'height': height,
} for height, extension in _formats]
# extract video metadata
2016-04-11 10:14:07 +02:00
title = remove_start(
self._html_search_meta('title', webpage, fatal=True), 'PressTV-')
2016-04-10 16:36:44 +02:00
thumbnail = self._og_search_thumbnail(webpage)
description = self._og_search_description(webpage)
2016-04-10 16:36:44 +02:00
upload_date = '%04d%02d%02d' % (
2016-04-11 10:14:07 +02:00
int(mobj.group('y')),
int(mobj.group('m')),
int(mobj.group('d')),
2016-04-10 16:36:44 +02:00
)
return {
'id': video_id,
2016-04-11 10:14:07 +02:00
'display_id': display_id,
'title': title,
'formats': formats,
'thumbnail': thumbnail,
'upload_date': upload_date,
'description': description
}