aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/historicfilms.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/historicfilms.py')
-rw-r--r--youtube_dl/extractor/historicfilms.py46
1 files changed, 46 insertions, 0 deletions
diff --git a/youtube_dl/extractor/historicfilms.py b/youtube_dl/extractor/historicfilms.py
new file mode 100644
index 000000000..40afbe537
--- /dev/null
+++ b/youtube_dl/extractor/historicfilms.py
@@ -0,0 +1,46 @@
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import parse_duration
+
+
+class HistoricFilmsIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?historicfilms\.com/(?:tapes/|play)(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://www.historicfilms.com/tapes/4728',
+ 'md5': 'd4a437aec45d8d796a38a215db064e9a',
+ 'info_dict': {
+ 'id': '4728',
+ 'ext': 'mov',
+ 'title': 'Historic Films: GP-7',
+ 'description': 'md5:1a86a0f3ac54024e419aba97210d959a',
+ 'thumbnail': 're:^https?://.*\.jpg$',
+ 'duration': 2096,
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ tape_id = self._search_regex(
+ r'class="tapeId">([^<]+)<', webpage, 'tape id')
+
+ title = self._og_search_title(webpage)
+ description = self._og_search_description(webpage)
+ thumbnail = self._html_search_meta(
+ 'thumbnailUrl', webpage, 'thumbnails') or self._og_search_thumbnail(webpage)
+ duration = parse_duration(self._html_search_meta(
+ 'duration', webpage, 'duration'))
+
+ video_url = 'http://www.historicfilms.com/video/%s_%s_web.mov' % (tape_id, video_id)
+
+ return {
+ 'id': video_id,
+ 'url': video_url,
+ 'title': title,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': duration,
+ }