From 4d8856d511aef11b5dbeb9f6523c2a117bdbb85d Mon Sep 17 00:00:00 2001 From: =?utf8?q?Sergey=20M=E2=80=A4?= Date: Sat, 4 Jun 2016 00:26:03 +0700 Subject: [PATCH] [loc] Extract direct download links --- youtube_dl/extractor/libraryofcongress.py | 38 ++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py index 49351759e..0a94366fd 100644 --- a/youtube_dl/extractor/libraryofcongress.py +++ b/youtube_dl/extractor/libraryofcongress.py @@ -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 @@ class LibraryOfCongressIE(InfoExtractor): 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 @@ class LibraryOfCongressIE(InfoExtractor): 'format_id': 'hls', 'ext': 'mp4', 'protocol': 'm3u8_native', + 'quality': 1, }] elif 'vod/mp3:' in media_url: formats = [{ @@ -82,9 +103,24 @@ class LibraryOfCongressIE(InfoExtractor): 'vcodec': 'none', }] + download_urls = set() + for m in re.finditer( + r']+value=(["\'])(?P.+?)\1[^>]+data-file-download=[^>]+>\s*(?P.+?)(?:(?: |\s+)\((?P.+?)\))?\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')) -- 2.22.2