youtube-dl/youtube_dl/extractor/libraryofcongress.py

154 lines
4.9 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
2016-06-04 02:26:03 +09:00
import re
from .common import InfoExtractor
2016-06-04 01:19:11 +09:00
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
2016-06-04 02:26:03 +09:00
parse_filesize,
2016-06-04 01:19:11 +09:00
)
class LibraryOfCongressIE(InfoExtractor):
2016-06-04 01:19:11 +09:00
IE_NAME = 'loc'
IE_DESC = 'Library of Congress'
_VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9a-z_.]+)'
_TESTS = [{
2016-06-04 01:55:22 +09:00
# embedded via <div class="media-player"
2016-06-04 01:19:11 +09:00
'url': 'http://loc.gov/item/90716351/',
2018-11-21 20:00:50 +09:00
'md5': '6ec0ae8f07f86731b1b2ff70f046210a',
'info_dict': {
'id': '90716351',
'ext': 'mp4',
2016-06-04 01:19:11 +09:00
'title': "Pa's trip to Mars",
'duration': 0,
'view_count': int,
},
}, {
2016-06-04 01:55:22 +09:00
# webcast embedded via mediaObjectId
'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
2016-06-04 01:55:22 +09:00
'info_dict': {
'id': '5578',
'ext': 'mp4',
'title': 'Help! Preservation Training Needs Here, There & Everywhere',
'duration': 3765,
'view_count': int,
'subtitles': 'mincount:1',
},
'params': {
'skip_download': True,
},
2016-06-04 02:26:03 +09:00
}, {
# with direct download links
'url': 'https://www.loc.gov/item/78710669/',
'info_dict': {
'id': '78710669',
'ext': 'mp4',
'title': 'La vie et la passion de Jesus-Christ',
'duration': 0,
'view_count': int,
'formats': 'mincount:4',
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.loc.gov/item/ihas.200197114/',
'only_matching': True,
}, {
'url': 'https://www.loc.gov/item/afc1981005_afs20503/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
2016-06-04 01:19:11 +09:00
media_id = self._search_regex(
(r'id=(["\'])media-player-(?P<id>.+?)\1',
r'<video[^>]+id=(["\'])uuid-(?P<id>.+?)\1',
r'<video[^>]+data-uuid=(["\'])(?P<id>.+?)\1',
r'mediaObjectId\s*:\s*(["\'])(?P<id>.+?)\1',
r'data-tab="share-media-(?P<id>[0-9A-F]{32})"'),
2016-06-04 01:19:11 +09:00
webpage, 'media id', group='id')
data = self._download_json(
'https://media.loc.gov/services/v1/media?id=%s&context=json' % media_id,
media_id)['mediaObject']
2016-06-04 01:19:11 +09:00
derivative = data['derivatives'][0]
media_url = derivative['derivativeUrl']
2016-06-04 02:26:03 +09:00
title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
webpage)
2016-06-04 01:19:11 +09:00
# Following algorithm was extracted from setAVSource js function
# found in webpage
media_url = media_url.replace('rtmp', 'https')
2016-06-04 01:19:11 +09:00
is_video = data.get('mediaType', 'v').lower() == 'v'
ext = determine_ext(media_url)
if ext not in ('mp4', 'mp3'):
media_url += '.mp4' if is_video else '.mp3'
formats = []
if '/vod/mp4:' in media_url:
formats.append({
'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8',
2016-06-04 01:19:11 +09:00
'format_id': 'hls',
'ext': 'mp4',
'protocol': 'm3u8_native',
2016-06-04 02:26:03 +09:00
'quality': 1,
})
http_format = {
'url': re.sub(r'(://[^/]+/)(?:[^/]+/)*(?:mp4|mp3):', r'\1', media_url),
'format_id': 'http',
'quality': 1,
}
if not is_video:
http_format['vcodec'] = 'none'
formats.append(http_format)
2016-06-04 01:19:11 +09:00
2016-06-04 02:26:03 +09:00
download_urls = set()
for m in re.finditer(
r'<option[^>]+value=(["\'])(?P<url>.+?)\1[^>]+data-file-download=[^>]+>\s*(?P<id>.+?)(?:(?:&nbsp;|\s+)\((?P<size>.+?)\))?\s*<', webpage):
format_id = m.group('id').lower()
if format_id in ('gif', 'jpeg'):
2016-06-04 02:26:03 +09:00
continue
download_url = m.group('url')
if download_url in download_urls:
continue
download_urls.add(download_url)
formats.append({
'url': download_url,
'format_id': format_id,
'filesize_approx': parse_filesize(m.group('size')),
})
2016-06-04 01:19:11 +09:00
self._sort_formats(formats)
2016-06-04 01:19:11 +09:00
duration = float_or_none(data.get('duration'))
view_count = int_or_none(data.get('viewCount'))
2016-06-04 01:55:22 +09:00
subtitles = {}
cc_url = data.get('ccUrl')
if cc_url:
subtitles.setdefault('en', []).append({
'url': cc_url,
'ext': 'ttml',
})
return {
'id': video_id,
2016-06-04 01:19:11 +09:00
'title': title,
'thumbnail': self._og_search_thumbnail(webpage, default=None),
2016-06-04 01:19:11 +09:00
'duration': duration,
'view_count': view_count,
'formats': formats,
2016-06-04 01:55:22 +09:00
'subtitles': subtitles,
}