X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/d1a5eac72c0b1116e8efbbf50766d8d00678f5c8..2e86127b07f6a63b7ce457331d600d9486b22b44:/youtube_dl/extractor/imdb.py diff --git a/youtube_dl/extractor/imdb.py b/youtube_dl/extractor/imdb.py index f40769e..f2c1c10 100644 --- a/youtube_dl/extractor/imdb.py +++ b/youtube_dl/extractor/imdb.py @@ -6,7 +6,6 @@ import json from .common import InfoExtractor from ..utils import ( compat_urlparse, - get_element_by_attribute, ) @@ -27,10 +26,11 @@ class ImdbIE(InfoExtractor): } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') + video_id = self._match_id(url) webpage = self._download_webpage('http://www.imdb.com/video/imdb/vi%s' % video_id, video_id) - descr = get_element_by_attribute('itemprop', 'description', webpage) + descr = self._html_search_regex( + r'(?s)(.*?)', + webpage, 'description', fatal=False) available_formats = re.findall( r'case \'(?P.*?)\' :$\s+url = \'(?P.*?)\'', webpage, flags=re.MULTILINE) @@ -63,27 +63,23 @@ class ImdbListIE(InfoExtractor): IE_NAME = 'imdb:list' IE_DESC = 'Internet Movie Database lists' _VALID_URL = r'http://www\.imdb\.com/list/(?P[\da-zA-Z_-]{11})' - + _TEST = { + 'url': 'http://www.imdb.com/list/JFs9NWw6XI0', + 'info_dict': { + 'id': 'JFs9NWw6XI0', + 'title': 'March 23, 2012 Releases', + }, + 'playlist_count': 7, + } + def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - list_id = mobj.group('id') - - # RSS XML is sometimes malformed - rss = self._download_webpage('http://rss.imdb.com/list/%s' % list_id, list_id, 'Downloading list RSS') - list_title = self._html_search_regex(r'(.*?)', rss, 'list title') - - # Export is independent of actual author_id, but returns 404 if no author_id is provided. - # However, passing dummy author_id seems to be enough. - csv = self._download_webpage('http://www.imdb.com/list/export?list_id=%s&author_id=ur00000000' % list_id, - list_id, 'Downloading list CSV') - - entries = [] - for item in csv.split('\n')[1:]: - cols = item.split(',') - if len(cols) < 2: - continue - item_id = cols[1][1:-1] - if item_id.startswith('vi'): - entries.append(self.url_result('http://www.imdb.com/video/imdb/%s' % item_id, 'Imdb')) - + list_id = self._match_id(url) + webpage = self._download_webpage(url, list_id) + entries = [ + self.url_result('http://www.imdb.com' + m, 'Imdb') + for m in re.findall(r'href="(/video/imdb/vi[^"]+)"\s+data-type="playlist"', webpage)] + + list_title = self._html_search_regex( + r'

(.*?)

', webpage, 'list title') + return self.playlist_result(entries, list_id, list_title)