youtube-dl/youtube_dl/extractor/imdb.py

132 lines
5.0 KiB
Python
Raw Normal View History

2014-01-07 09:41:13 +01:00
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..compat import compat_str
2015-10-18 14:13:06 +02:00
from ..utils import (
determine_ext,
2016-05-13 19:25:05 +02:00
mimetype2ext,
2015-10-18 14:13:06 +02:00
qualities,
remove_end,
)
class ImdbIE(InfoExtractor):
2014-01-07 09:41:13 +01:00
IE_NAME = 'imdb'
IE_DESC = 'Internet Movie Database trailers'
_VALID_URL = r'https?://(?:www|m)\.imdb\.com/(?:video|title).+?[/-]vi(?P<id>\d+)'
2016-05-13 18:19:00 +02:00
_TESTS = [{
2014-01-07 09:41:13 +01:00
'url': 'http://www.imdb.com/video/imdb/vi2524815897',
'info_dict': {
'id': '2524815897',
'ext': 'mp4',
'title': 'Ice Age: Continental Drift Trailer (No. 2)',
2014-01-07 09:41:13 +01:00
'description': 'md5:9061c2219254e5d14e03c25c98e96a81',
}
2016-05-13 18:19:00 +02:00
}, {
'url': 'http://www.imdb.com/video/_/vi2524815897',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/title/tt1667889/?ref_=ext_shr_eml_vi#lb-vi2524815897',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/title/tt1667889/#lb-vi2524815897',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/videoplayer/vi1562949145',
'only_matching': True,
}, {
'url': 'http://www.imdb.com/title/tt4218696/videoplayer/vi2608641561',
'only_matching': True,
2016-05-13 18:19:00 +02:00
}]
def _real_extract(self, url):
2014-11-04 23:26:23 +01:00
video_id = self._match_id(url)
webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id)
2014-11-04 23:26:23 +01:00
descr = self._html_search_regex(
r'(?s)<span itemprop="description">(.*?)</span>',
webpage, 'description', fatal=False)
2015-10-18 14:13:06 +02:00
player_url = 'http://www.imdb.com/video/imdb/vi%s/imdb/single' % video_id
player_page = self._download_webpage(
player_url, video_id, 'Downloading player page')
# the player page contains the info for the default format, we have to
# fetch other pages for the rest of the formats
extra_formats = re.findall(r'href="(?P<url>%s.*?)".*?>(?P<name>.*?)<' % re.escape(player_url), player_page)
format_pages = [
self._download_webpage(
f_url, video_id, 'Downloading info for %s format' % f_name)
for f_url, f_name in extra_formats]
format_pages.append(player_page)
quality = qualities(('SD', '480p', '720p', '1080p'))
formats = []
2015-10-18 14:13:06 +02:00
for format_page in format_pages:
json_data = self._search_regex(
r'<script[^>]+class="imdb-player-data"[^>]*?>(.*?)</script>',
2014-01-07 09:41:13 +01:00
format_page, 'json data', flags=re.DOTALL)
2016-05-13 19:25:05 +02:00
info = self._parse_json(json_data, video_id, fatal=False)
if not info:
continue
format_info = info.get('videoPlayerObject', {}).get('video', {})
if not format_info:
continue
video_info_list = format_info.get('videoInfoList')
if not video_info_list or not isinstance(video_info_list, list):
continue
for video_info in video_info_list:
if not video_info or not isinstance(video_info, dict):
continue
video_url = video_info.get('videoUrl')
if not video_url or not isinstance(video_url, compat_str):
continue
if (video_info.get('videoMimeType') == 'application/x-mpegURL' or
determine_ext(video_url) == 'm3u8'):
formats.extend(self._extract_m3u8_formats(
video_url, video_id, 'mp4', entry_protocol='m3u8_native',
m3u8_id='hls', fatal=False))
continue
format_id = format_info.get('ffname')
formats.append({
'format_id': format_id,
'url': video_url,
'ext': mimetype2ext(video_info.get('videoMimeType')),
'quality': quality(format_id),
})
2015-10-18 14:13:06 +02:00
self._sort_formats(formats)
return {
'id': video_id,
'title': remove_end(self._og_search_title(webpage), ' - IMDb'),
'formats': formats,
'description': descr,
'thumbnail': format_info.get('slate'),
}
2013-12-25 02:34:41 +01:00
2014-01-07 09:41:13 +01:00
2013-12-25 02:34:41 +01:00
class ImdbListIE(InfoExtractor):
2014-01-07 09:41:13 +01:00
IE_NAME = 'imdb:list'
IE_DESC = 'Internet Movie Database lists'
2016-09-08 13:29:05 +02:00
_VALID_URL = r'https?://(?:www\.)?imdb\.com/list/(?P<id>[\da-zA-Z_-]{11})'
_TEST = {
'url': 'http://www.imdb.com/list/JFs9NWw6XI0',
'info_dict': {
'id': 'JFs9NWw6XI0',
'title': 'March 23, 2012 Releases',
},
'playlist_count': 7,
}
2014-11-23 20:41:03 +01:00
2013-12-25 02:34:41 +01:00
def _real_extract(self, url):
2014-11-04 23:26:23 +01:00
list_id = self._match_id(url)
webpage = self._download_webpage(url, list_id)
entries = [
self.url_result('http://www.imdb.com' + m, 'Imdb')
2014-01-28 03:12:23 +01:00
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 09:41:13 +01:00
return self.playlist_result(entries, list_id, list_title)