mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-10-30 22:25:19 +00:00
Code Issues Projects Releases Wiki Activity

[hearthisat] Detect invalid download links (fixes #9440)

Browse Source
This commit is contained in:
Yen Chi Hsuan
2016-05-15 15:35:31 +08:00
parent 79298173c5
commit cec9727c7f
1 changed files with 29 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
youtube_dl/extractor/hearthisat.py
View File

@@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..compat import compat_urlparse from ..compat import compat_urlparse
from ..utils import ( from ..utils import (
HEADRequest, HEADRequest,
KNOWN_EXTENSIONS,
sanitized_Request, sanitized_Request,
str_to_int, str_to_int,
urlencode_postdata, urlencode_postdata,
@@ -17,7 +18,7 @@ from ..utils import (
class HearThisAtIE(InfoExtractor): class HearThisAtIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$' _VALID_URL = r'https?://(?:www\.)?hearthis\.at/(?P<artist>[^/]+)/(?P<title>[A-Za-z0-9\-]+)/?$'
_PLAYLIST_URL = 'https://hearthis.at/playlist.php' _PLAYLIST_URL = 'https://hearthis.at/playlist.php'
_TEST = { _TESTS = [{
'url': 'https://hearthis.at/moofi/dr-kreep', 'url': 'https://hearthis.at/moofi/dr-kreep',
'md5': 'ab6ec33c8fed6556029337c7885eb4e0', 'md5': 'ab6ec33c8fed6556029337c7885eb4e0',
'info_dict': { 'info_dict': {
@@ -34,7 +35,25 @@ class HearThisAtIE(InfoExtractor):
'duration': 71, 'duration': 71,
'categories': ['Experimental'], 'categories': ['Experimental'],
} }
} }, {
# 'download' link redirects to the original webpage
'url': 'https://hearthis.at/twitchsf/dj-jim-hopkins-totally-bitchin-80s-dance-mix/',
'md5': '5980ceb7c461605d30f1f039df160c6e',
'info_dict': {
'id': '811296',
'ext': 'mp3',
'title': 'TwitchSF - DJ Jim Hopkins - Totally Bitchin\' 80\'s Dance Mix!',
'description': 'Listen to DJ Jim Hopkins - Totally Bitchin\' 80\'s Dance Mix! by TwitchSF on hearthis.at - Dance',
'upload_date': '20160328',
'timestamp': 1459186146,
'thumbnail': 're:^https?://.*\.jpg$',
'comment_count': int,
'view_count': int,
'like_count': int,
'duration': 4360,
'categories': ['Dance'],
},
}]
def _real_extract(self, url): def _real_extract(self, url):
m = re.match(self._VALID_URL, url) m = re.match(self._VALID_URL, url)
@@ -90,13 +109,14 @@ class HearThisAtIE(InfoExtractor):
ext_handle = self._request_webpage( ext_handle = self._request_webpage(
ext_req, display_id, note='Determining extension') ext_req, display_id, note='Determining extension')
ext = urlhandle_detect_ext(ext_handle) ext = urlhandle_detect_ext(ext_handle)
formats.append({ if ext in KNOWN_EXTENSIONS:
'format_id': 'download', formats.append({
'vcodec': 'none', 'format_id': 'download',
'ext': ext, 'vcodec': 'none',
'url': download_url, 'ext': ext,
'preference': 2, # Usually better quality 'url': download_url,
}) 'preference': 2, # Usually better quality
})
self._sort_formats(formats) self._sort_formats(formats)
return { return {