From d8d6148628b972b6998a8c2a5465f031a44f4004 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 28 Nov 2013 13:32:49 +0100 Subject: [PATCH] Add an extractor for Internet Movie Database trailers (closes #1832) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/imdb.py | 59 ++++++++++++++++++++++++++++++++ 2 files changed, 60 insertions(+) create mode 100644 youtube_dl/extractor/imdb.py 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 .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\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.*?)\' :$\s+url = \'(?P.*?)\'', 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']), + }