aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-11-28 13:32:49 +0100
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-11-28 13:32:49 +0100
commitd8d6148628b972b6998a8c2a5465f031a44f4004 (patch)
treef9f6c9a722f4ab7ebc3156c873d2d5e9303d05ce /youtube_dl
parent2be54167d085c5b4c956c66ad0367fdcfb68b891 (diff)
Add an extractor for Internet Movie Database trailers (closes #1832)
Diffstat (limited to 'youtube_dl')
-rw-r--r--youtube_dl/extractor/__init__.py1
-rw-r--r--youtube_dl/extractor/imdb.py59
2 files changed, 60 insertions, 0 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 0b4d086b7..30e4a9105 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -71,6 +71,7 @@ from .hotnewhiphop import HotNewHipHopIE
from .howcast import HowcastIE
from .hypem import HypemIE
from .ign import IGNIE, OneUPIE
+from .imdb import ImdbIE
from .ina import InaIE
from .infoq import InfoQIE
from .instagram import InstagramIE
diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py
new file mode 100644
index 000000000..07e4f7d29
--- /dev/null
+++ b/youtube_dl/extractor/imdb.py
@@ -0,0 +1,59 @@
+import re
+import json
+
+from .common import InfoExtractor
+from ..utils import (
+ compat_urlparse,
+ get_element_by_attribute,
+)
+
+
+class ImdbIE(InfoExtractor):
+ IE_NAME = u'imdb'
+ IE_DESC = u'Internet Movie Database trailers'
+ _VALID_URL = r'http://www\.imdb\.com/video/imdb/vi(?P<id>\d+)'
+
+ _TEST = {
+ u'url': u'http://www.imdb.com/video/imdb/vi2524815897',
+ u'md5': u'9f34fa777ade3a6e57a054fdbcb3a068',
+ u'info_dict': {
+ u'id': u'2524815897',
+ u'ext': u'mp4',
+ u'title': u'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
+ u'description': u'md5:9061c2219254e5d14e03c25c98e96a81',
+ u'duration': 151,
+ }
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ video_id = mobj.group('id')
+ webpage = self._download_webpage(url,video_id)
+ descr = get_element_by_attribute('itemprop', 'description', webpage)
+ available_formats = re.findall(
+ r'case \'(?P<f_id>.*?)\' :$\s+url = \'(?P<path>.*?)\'', webpage,
+ flags=re.MULTILINE)
+ formats = []
+ for f_id, f_path in available_formats:
+ format_page = self._download_webpage(
+ compat_urlparse.urljoin(url, f_path),
+ u'Downloading info for %s format' % f_id)
+ json_data = get_element_by_attribute('class', 'imdb-player-data',
+ format_page)
+ info = json.loads(json_data)
+ format_info = info['videoPlayerObject']['video']
+ formats.append({
+ 'format_id': f_id,
+ 'url': format_info['url'],
+ 'height': format_info['height'],
+ 'width': format_info['width'],
+ })
+
+ return {
+ 'id': video_id,
+ 'title': self._og_search_title(webpage),
+ 'formats': formats,
+ 'description': descr,
+ 'thumbnail': format_info['slate'],
+ 'duration': int(info['titleObject']['title']['duration_seconds']),
+ }