1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00

[loc] Add extractor (Closes #3188)

Added extractor of loc.gov, which closes #3188. I am not an experienced programmer, so I am sure I did a bunch of mistakes, but the extractor works (for me at least).

[LibraryOfCongress] don't use video_id for _search_regex()

[LibraryOfCongress] Improvements
This commit is contained in:
TRox1972 2016-05-17 16:21:52 +02:00 committed by Sergey M․
parent ad73083ff0
commit 9c3c447eb3
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 66 additions and 0 deletions

View file

@ -382,6 +382,7 @@ from .leeco import (
LePlaylistIE,
LetvCloudIE,
)
from .libraryofcongress import LibraryOfCongressIE
from .libsyn import LibsynIE
from .lifenews import (
LifeNewsIE,

View file

@ -0,0 +1,65 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import determine_ext
class LibraryOfCongressIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?loc\.gov/item/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'http://loc.gov/item/90716351/',
'info_dict': {
'id': '90716351',
'ext': 'mp4',
'title': 'Pa\'s trip to Mars /'
},
'params': {
# m3u8 download
'skip_download': True,
}
}, {
'url': 'https://www.loc.gov/item/97516576/',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
self.report_extraction(video_id)
json_id = self._search_regex('media-player-([0-9A-Z]{32})', webpage, 'json id')
data = self._parse_json(self._download_webpage(
'https://media.loc.gov/services/v1/media?id=%s' % json_id,
video_id), video_id)
data = data['mediaObject']
media_url = data['derivatives'][0]['derivativeUrl']
media_url = media_url.replace('rtmp', 'https')
is_video = data['mediaType'].lower() == 'v'
if not determine_ext(media_url) in ('mp4', 'mp3'):
media_url += '.mp4' if is_video else '.mp3'
if media_url.index('vod/mp4:') > -1:
media_url = media_url.replace('vod/mp4:', 'hls-vod/media/') + '.m3u8'
elif url.index('vod/mp3:') > -1:
media_url = media_url.replace('vod/mp3:', '')
formats = []
if determine_ext(media_url) == 'm3u8':
formats = self._extract_m3u8_formats(media_url, video_id, ext='mp4')
elif determine_ext(media_url) is 'mp3':
formats.append({
'url': media_url,
'ext': 'mp3',
})
return {
'id': video_id,
'thumbnail': self._og_search_thumbnail(webpage),
'title': self._og_search_title(webpage),
'formats': formats,
}