X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Flibraryofcongress.py;h=40295a30b51f733b637c651cc8a434ede14f517a;hb=54fc90aabfb71968f28af68dfe3f7a3544cc2f0b;hp=a5f22b2048671291ca08425859cb6a044cf93f21;hpb=76e9cd7f24f6b175e4cce85082647403266ed233;p=youtube-dl

diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py
index a5f22b204..40295a30b 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,
 )
 
 
@@ -15,19 +18,45 @@ class LibraryOfCongressIE(InfoExtractor):
     IE_DESC = 'Library of Congress'
     _VALID_URL = r'https?://(?:www\.)?loc\.gov/(?:item/|today/cyberlc/feature_wdesc\.php\?.*\brec=)(?P<id>[0-9]+)'
     _TESTS = [{
+        # embedded via <div class="media-player"
         'url': 'http://loc.gov/item/90716351/',
         'md5': '353917ff7f0255aa6d4b80a034833de8',
         'info_dict': {
             'id': '90716351',
             'ext': 'mp4',
             'title': "Pa's trip to Mars",
-            'thumbnail': 're:^https?://.*\.jpg$',
+            'thumbnail': r're:^https?://.*\.jpg$',
             'duration': 0,
             'view_count': int,
         },
     }, {
+        # webcast embedded via mediaObjectId
         'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
-        'only_matching': True,
+        '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,
+        },
+    }, {
+        # 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):
@@ -48,6 +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')
@@ -63,6 +95,7 @@ class LibraryOfCongressIE(InfoExtractor):
                 'format_id': 'hls',
                 'ext': 'mp4',
                 'protocol': 'm3u8_native',
+                'quality': 1,
             }]
         elif 'vod/mp3:' in media_url:
             formats = [{
@@ -70,12 +103,35 @@ class LibraryOfCongressIE(InfoExtractor):
                 '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'))
 
+        subtitles = {}
+        cc_url = data.get('ccUrl')
+        if cc_url:
+            subtitles.setdefault('en', []).append({
+                'url': cc_url,
+                'ext': 'ttml',
+            })
+
         return {
             'id': video_id,
             'title': title,
@@ -83,4 +139,5 @@ class LibraryOfCongressIE(InfoExtractor):
             'duration': duration,
             'view_count': view_count,
             'formats': formats,
+            'subtitles': subtitles,
         }