X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Flibraryofcongress.py;h=03f2051444d63bb046b6b5943cc5400085c6d8d3;hb=HEAD;hp=0c34dbce32d6eaa4f08ecbea8c97d9fbd2f4802e;hpb=9c3c447eb389726d98189d972a2d772ef729132d;p=youtube-dl

diff --git a/youtube_dl/extractor/libraryofcongress.py b/youtube_dl/extractor/libraryofcongress.py
index 0c34dbce3..03f205144 100644
--- a/youtube_dl/extractor/libraryofcongress.py
+++ b/youtube_dl/extractor/libraryofcongress.py
@@ -1,26 +1,66 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 
-from ..utils import determine_ext
+from ..utils import (
+    determine_ext,
+    float_or_none,
+    int_or_none,
+    parse_filesize,
+)
 
 
 class LibraryOfCongressIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?loc\.gov/item/(?P<id>[0-9]+)'
+    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 = [{
-    'url': 'http://loc.gov/item/90716351/',
+        # embedded via <div class="media-player"
+        'url': 'http://loc.gov/item/90716351/',
+        'md5': '6ec0ae8f07f86731b1b2ff70f046210a',
         'info_dict': {
             'id': '90716351',
             'ext': 'mp4',
-            'title': 'Pa\'s trip to Mars /'
+            'title': "Pa's trip to Mars",
+            'duration': 0,
+            'view_count': int,
+        },
+    }, {
+        # webcast embedded via mediaObjectId
+        'url': 'https://www.loc.gov/today/cyberlc/feature_wdesc.php?rec=5578',
+        'info_dict': {
+            'id': '5578',
+            'ext': 'mp4',
+            'title': 'Help! Preservation Training Needs Here, There & Everywhere',
+            'duration': 3765,
+            'view_count': int,
+            'subtitles': 'mincount:1',
         },
         'params': {
-            # m3u8 download
             '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,
+        },
     }, {
-        'url': 'https://www.loc.gov/item/97516576/',
+        'url': 'https://www.loc.gov/item/ihas.200197114/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.loc.gov/item/afc1981005_afs20503/',
         'only_matching': True,
     }]
 
@@ -28,38 +68,86 @@ class LibraryOfCongressIE(InfoExtractor):
         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')
+        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})"'),
+            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']
+
+        derivative = data['derivatives'][0]
+        media_url = derivative['derivativeUrl']
 
-        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']
+        title = derivative.get('shortName') or data.get('shortName') or self._og_search_title(
+            webpage)
 
-        media_url = data['derivatives'][0]['derivativeUrl']
+        # Following algorithm was extracted from setAVSource js function
+        # found in webpage
         media_url = media_url.replace('rtmp', 'https')
 
-        is_video = data['mediaType'].lower() == 'v'
-        if not determine_ext(media_url) in ('mp4', 'mp3'):
+        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'
 
-        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':
+        if '/vod/mp4:' in media_url:
             formats.append({
-                'url': media_url,
-                'ext': 'mp3',
+                'url': media_url.replace('/vod/mp4:', '/hls-vod/media/') + '.m3u8',
+                'format_id': 'hls',
+                'ext': 'mp4',
+                'protocol': 'm3u8_native',
+                '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)
+
+        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'):
+                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)
+
+        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,
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'title': self._og_search_title(webpage),
+            'title': title,
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'duration': duration,
+            'view_count': view_count,
             'formats': formats,
+            'subtitles': subtitles,
         }