yt-dlc/youtube_dlc/extractor/ina.py

87 lines
2.9 KiB
Python
Raw Normal View History

2016-10-02 13:39:18 +02:00
# coding: utf-8
from __future__ import unicode_literals
2013-06-23 22:28:19 +02:00
from .common import InfoExtractor
2019-03-27 18:29:24 +01:00
from ..utils import (
2019-03-27 18:49:29 +01:00
determine_ext,
2019-03-27 18:29:24 +01:00
int_or_none,
strip_or_none,
xpath_attr,
xpath_text,
)
2013-06-23 22:28:19 +02:00
class InaIE(InfoExtractor):
2020-11-27 23:51:33 +01:00
_VALID_URL = r'https?://(?:(?:www|m)\.)?ina\.fr/(?:video|audio)/(?P<id>[A-Z0-9_]+)'
2019-03-27 18:29:24 +01:00
_TESTS = [{
'url': 'http://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
'md5': 'a667021bf2b41f8dc6049479d9bb38a3',
'info_dict': {
'id': 'I12055569',
'ext': 'mp4',
'title': 'François Hollande "Je crois que c\'est clair"',
2019-03-27 18:29:24 +01:00
'description': 'md5:3f09eb072a06cb286b8f7e4f77109663',
2013-06-27 20:46:46 +02:00
}
2019-03-27 18:29:24 +01:00
}, {
'url': 'https://www.ina.fr/video/S806544_001/don-d-organes-des-avancees-mais-d-importants-besoins-video.html',
'only_matching': True,
2019-03-27 18:49:29 +01:00
}, {
'url': 'https://www.ina.fr/audio/P16173408',
'only_matching': True,
}, {
'url': 'https://www.ina.fr/video/P16173408-video.html',
'only_matching': True,
2020-11-27 23:51:33 +01:00
}, {
'url': 'http://m.ina.fr/video/I12055569',
'only_matching': True,
2019-03-27 18:29:24 +01:00
}]
2013-06-23 22:28:19 +02:00
def _real_extract(self, url):
2019-03-27 18:29:24 +01:00
video_id = self._match_id(url)
info_doc = self._download_xml(
'http://player.ina.fr/notices/%s.mrss' % video_id, video_id)
item = info_doc.find('channel/item')
title = xpath_text(item, 'title', fatal=True)
media_ns_xpath = lambda x: self._xpath_ns(x, 'http://search.yahoo.com/mrss/')
content = item.find(media_ns_xpath('content'))
2013-06-23 22:28:19 +02:00
2019-03-27 18:29:24 +01:00
get_furl = lambda x: xpath_attr(content, media_ns_xpath(x), 'url')
formats = []
for q, w, h in (('bq', 400, 300), ('mq', 512, 384), ('hq', 768, 576)):
q_url = get_furl(q)
if not q_url:
continue
formats.append({
'format_id': q,
'url': q_url,
'width': w,
'height': h,
})
if not formats:
2019-03-27 18:49:29 +01:00
furl = get_furl('player') or content.attrib['url']
ext = determine_ext(furl)
2019-03-27 18:29:24 +01:00
formats = [{
2019-03-27 18:49:29 +01:00
'url': furl,
'vcodec': 'none' if ext == 'mp3' else None,
'ext': ext,
2019-03-27 18:29:24 +01:00
}]
2013-06-23 22:28:19 +02:00
2019-03-27 18:29:24 +01:00
thumbnails = []
for thumbnail in content.findall(media_ns_xpath('thumbnail')):
thumbnail_url = thumbnail.get('url')
if not thumbnail_url:
continue
thumbnails.append({
'url': thumbnail_url,
'height': int_or_none(thumbnail.get('height')),
'width': int_or_none(thumbnail.get('width')),
})
2013-06-23 22:28:19 +02:00
return {
'id': video_id,
2019-03-27 18:29:24 +01:00
'formats': formats,
'title': title,
'description': strip_or_none(xpath_text(item, 'description')),
'thumbnails': thumbnails,
}