github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[loc] Extract direct download links

Browse source
This commit is contained in:
Sergey M․ 2016-06-04 00:26:03 +07:00
parent c917106be4
commit 4d8856d511
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 37 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
youtube_dl/extractor/libraryofcongress.py
View file

@ -1,12 +1,15 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
parse_filesize,
)
@ -40,6 +43,20 @@ class LibraryOfCongressIE(InfoExtractor):
'params': {
'skip_download': True,
},
}, {
# 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,
},
}]
def _real_extract(self, url):
@ -60,6 +77,9 @@ def _real_extract(self, url):
derivative = data['derivatives'][0]
media_url = derivative['derivativeUrl']
title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
webpage)
# Following algorithm was extracted from setAVSource js function
# found in webpage
media_url = media_url.replace('rtmp', 'https')
@ -75,6 +95,7 @@ def _real_extract(self, url):
'format_id': 'hls',
'ext': 'mp4',
'protocol': 'm3u8_native',
'quality': 1,
}]
elif 'vod/mp3:' in media_url:
formats = [{
@ -82,9 +103,24 @@ def _real_extract(self, url):
'vcodec': 'none',
}]
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 == 'gif':
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')),
})
self._sort_formats(formats)
title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(webpage)
duration = float_or_none(data.get('duration'))
view_count = int_or_none(data.get('viewCount'))