1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-22 22:25:27 +08:00
youtube-dl/youtube_dl/extractor/imdb.py

80 lines
2.7 KiB
Python
Raw Normal View History

2014-01-07 16:41:13 +08:00
from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
compat_urlparse,
get_element_by_attribute,
)
class ImdbIE(InfoExtractor):
2014-01-07 16:41:13 +08:00
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
_VALID_URL = r'http://(?:www|m)\.imdb\.com/video/imdb/vi(?P<id>\d+)'
_TEST = {
2014-01-07 16:41:13 +08:00
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
'md5': '9f34fa777ade3a6e57a054fdbcb3a068',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
'title': 'Ice Age: Continental Drift Trailer (No. 2) - IMDb',
'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, 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:
f_path = f_path.strip()
format_page = self._download_webpage(
compat_urlparse.urljoin(url, f_path),
2014-01-07 16:41:13 +08:00
'Downloading info for %s format' % f_id)
json_data = self._search_regex(
r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
2014-01-07 16:41:13 +08:00
format_page, 'json data', flags=re.DOTALL)
info = json.loads(json_data)
format_info = info['videoPlayerObject']['video']
formats.append({
'format_id': f_id,
'url': format_info['url'],
})
return {
'id': video_id,
'title': self._og_search_title(webpage),
'formats': formats,
'description': descr,
'thumbnail': format_info['slate'],
}
2013-12-25 09:34:41 +08:00
2014-01-07 16:41:13 +08:00
2013-12-25 09:34:41 +08:00
class ImdbListIE(InfoExtractor):
2014-01-07 16:41:13 +08:00
IE_NAME = 'imdb:list'
IE_DESC = 'Internet Movie Database lists'
2013-12-25 09:34:41 +08:00
_VALID_URL = r'http://www\.imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
list_id = mobj.group('id')
webpage = self._download_webpage(url, list_id)
entries = [
self.url_result('http://www.imdb.com' + m, 'Imdb')
2014-01-28 10:12:23 +08:00
for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)]
list_title = self._html_search_regex(
r'<h1 class="header">(.*?)</h1>', webpage, 'list title')
2014-01-07 16:41:13 +08:00
return self.playlist_result(entries, list_id, list_title)