fenix
/
yt-dlp
mirror of https://github.com/yt-dlp/yt-dlp.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[extractor/iwara:user] Make paging better (#3901) 

Authored by: Lesmiscore
This commit is contained in:
Lesmiscore 2022-05-31 10:52:42 +09:00 committed by GitHub
parent 222a230871
commit 661e7253a2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 52 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

70
yt_dlp/extractor/iwara.py
View File

@ -1,3 +1,4 @@
import itertools
import re import re
import urllib import urllib
@ -171,37 +172,70 @@ class IwaraUserIE(IwaraBaseIE):
IE_NAME = 'iwara:user' IE_NAME = 'iwara:user'
_TESTS = [{ _TESTS = [{
'url': 'https://ecchi.iwara.tv/users/CuteMMD', 'note': 'number of all videos page is just 1 page. less than 40 videos',
'url': 'https://ecchi.iwara.tv/users/infinityyukarip',
'info_dict': { 'info_dict': {
'id': 'CuteMMD', 'title': 'Uploaded videos from Infinity_YukariP',
'id': 'infinityyukarip',
'uploader': 'Infinity_YukariP',
'uploader_id': 'infinityyukarip',
}, },
'playlist_mincount': 198, 'playlist_mincount': 39,
}, { }, {
# urlencoded 'note': 'no even all videos page. probably less than 10 videos',
'url': 'https://ecchi.iwara.tv/users/%E5%92%95%E5%98%BF%E5%98%BF', 'url': 'https://ecchi.iwara.tv/users/mmd-quintet',
'info_dict': { 'info_dict': {
'id': '咕嘿嘿', 'title': 'Uploaded videos from mmd quintet',
'id': 'mmd-quintet',
'uploader': 'mmd quintet',
'uploader_id': 'mmd-quintet',
}, },
'playlist_mincount': 141, 'playlist_mincount': 6,
}, {
'note': 'has paging. more than 40 videos',
'url': 'https://ecchi.iwara.tv/users/theblackbirdcalls',
'info_dict': {
'title': 'Uploaded videos from TheBlackbirdCalls',
'id': 'theblackbirdcalls',
'uploader': 'TheBlackbirdCalls',
'uploader_id': 'theblackbirdcalls',
},
'playlist_mincount': 420,
}, {
'note': 'foreign chars in URL. there must be foreign characters in URL',
'url': 'https://ecchi.iwara.tv/users/ぶた丼',
'info_dict': {
'title': 'Uploaded videos from ぶた丼',
'id': 'ぶた丼',
'uploader': 'ぶた丼',
'uploader_id': 'ぶた丼',
},
'playlist_mincount': 170,
}] }]
def _entries(self, playlist_id, base_url, webpage): def _entries(self, playlist_id, base_url):
yield from self._extract_playlist(base_url, webpage) webpage = self._download_webpage(
f'{base_url}/users/{playlist_id}', playlist_id)
videos_url = self._search_regex(r'<a href="(/users/[^/]+/videos)(?:\?[^"]+)?">', webpage, 'all videos url', default=None)
if not videos_url:
yield from self._extract_playlist(base_url, webpage)
return
page_urls = re.findall( videos_url = urljoin(base_url, videos_url)
r'class="pager-item"[^>]*>\s*<a[^<]+href="([^"]+)', webpage)
for n, path in enumerate(page_urls, 2): for n in itertools.count(1):
page = self._download_webpage(
videos_url, playlist_id, note=f'Downloading playlist page {n}',
query={'page': str(n - 1)} if n > 1 else {})
yield from self._extract_playlist( yield from self._extract_playlist(
base_url, self._download_webpage( base_url, page)
urljoin(base_url, path), playlist_id, note=f'Downloading playlist page {n}'))
if f'page={n}' not in page:
break
def _real_extract(self, url): def _real_extract(self, url):
playlist_id, base_url = self._match_valid_url(url).group('id', 'base_url') playlist_id, base_url = self._match_valid_url(url).group('id', 'base_url')
playlist_id = urllib.parse.unquote(playlist_id) playlist_id = urllib.parse.unquote(playlist_id)
webpage = self._download_webpage(
f'{base_url}/users/{playlist_id}/videos', playlist_id)
return self.playlist_result( return self.playlist_result(
self._entries(playlist_id, base_url, webpage), playlist_id) self._entries(playlist_id, base_url), playlist_id)