ansol/youtube-dl
7
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-25 06:15:46 +00:00
Code Issues Projects Releases Wiki Activity

[youku:show] Refine playlist extraction

Browse Source 
Handle playlists that the initial page is not the first page
This commit is contained in:
Yen Chi Hsuan 2017-07-20 23:20:46 +08:00
parent fa63cf6c23
commit 3fcf346ac1
No known key found for this signature in database
GPG Key ID: 7F902A182457CA23
1 changed files with 23 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

34
youtube_dl/extractor/youku.py
View File

@ -13,7 +13,6 @@ from ..utils import (
js_to_json, js_to_json,
str_or_none, str_or_none,
strip_jsonp, strip_jsonp,
urljoin,
) )
@ -238,13 +237,16 @@ class YoukuShowIE(InfoExtractor):
'description': 'md5:275715156abebe5ccc2a1992e9d56b98', 'description': 'md5:275715156abebe5ccc2a1992e9d56b98',
}, },
'playlist_count': 24, 'playlist_count': 24,
}, {
# Ongoing playlist. The initial page is the last one
'url': 'http://list.youku.com/show/id_za7c275ecd7b411e1a19e.html',
'only_matchine': True,
}] }]
def _extract_entries(self, playlist_data_url, show_id, idx, query, url): def _extract_entries(self, playlist_data_url, show_id, note, query):
query['callback'] = 'cb' query['callback'] = 'cb'
playlist_data = self._download_json( playlist_data = self._download_json(
playlist_data_url, show_id, query=query, playlist_data_url, show_id, query=query, note=note,
note='Downloading playlist data page %d' % (idx + 1),
transform_source=lambda s: js_to_json(strip_jsonp(s)))['html'] transform_source=lambda s: js_to_json(strip_jsonp(s)))['html']
drama_list = (get_element_by_class('p-drama-grid', playlist_data) or drama_list = (get_element_by_class('p-drama-grid', playlist_data) or
get_element_by_class('p-drama-half-row', playlist_data)) get_element_by_class('p-drama-half-row', playlist_data))
@ -252,29 +254,39 @@ class YoukuShowIE(InfoExtractor):
raise ExtractorError('No episodes found') raise ExtractorError('No episodes found')
video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list) video_urls = re.findall(r'<a[^>]+href="([^"]+)"', drama_list)
return playlist_data, [ return playlist_data, [
self.url_result(urljoin(url, video_url), YoukuIE.ie_key()) self.url_result(self._proto_relative_url(video_url, 'http:'), YoukuIE.ie_key())
for video_url in video_urls] for video_url in video_urls]
def _real_extract(self, url): def _real_extract(self, url):
show_id = self._match_id(url) show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id) webpage = self._download_webpage(url, show_id)
entries = []
page_config = self._parse_json(self._search_regex( page_config = self._parse_json(self._search_regex(
r'var\s+PageConfig\s*=\s*({.+});', webpage, 'page config'), r'var\s+PageConfig\s*=\s*({.+});', webpage, 'page config'),
show_id, transform_source=js_to_json) show_id, transform_source=js_to_json)
first_page, entries = self._extract_entries( first_page, initial_entries = self._extract_entries(
'http://list.youku.com/show/module', show_id, 0, { 'http://list.youku.com/show/module', show_id,
note='Downloading initial playlist data page',
query={
'id': page_config['showid'], 'id': page_config['showid'],
'tab': 'showInfo', 'tab': 'showInfo',
}, url) })
first_page_reload_id = self._html_search_regex(
r'<div[^>]+id="(reload_\d+)', first_page, 'first page reload id')
# The first reload_id has the same items as first_page # The first reload_id has the same items as first_page
reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page)[1:] reload_ids = re.findall('<li[^>]+data-id="([^"]+)">', first_page)
for idx, reload_id in enumerate(reload_ids): for idx, reload_id in enumerate(reload_ids):
if reload_id == first_page_reload_id:
entries.extend(initial_entries)
continue
_, new_entries = self._extract_entries( _, new_entries = self._extract_entries(
'http://list.youku.com/show/episode', show_id, idx + 1, { 'http://list.youku.com/show/episode', show_id,
note='Downloading playlist data page %d' % (idx + 1),
query={
'id': page_config['showid'], 'id': page_config['showid'],
'stage': reload_id, 'stage': reload_id,
}, url) })
entries.extend(new_entries) entries.extend(new_entries)
desc = self._html_search_meta('description', webpage, fatal=False) desc = self._html_search_meta('description', webpage, fatal=False)