github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[khinsider] fix extraction

Browse Source
This commit is contained in:
Mike Fährmann
2017-12-01 13:58:06 +01:00
parent 3dc1169736
commit 2b9a783fc7
1 changed files with 3 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
gallery_dl/extractor/khinsider.py
View File

@@ -44,6 +44,8 @@ class KhinsiderSoundtrackExtractor(AsynchronousExtractor):
def get_job_metadata(self, page): def get_job_metadata(self, page):
"""Collect metadata for extractor-job""" """Collect metadata for extractor-job"""
if "Download all songs at once:" not in page:
raise exception.NotFoundError("soundtrack")
data = text.extract_all(page, ( data = text.extract_all(page, (
("album", "Album name: <b>", "</b>"), ("album", "Album name: <b>", "</b>"),
("count", "Number of Files: <b>", "</b>"), ("count", "Number of Files: <b>", "</b>"),
@@ -56,10 +58,7 @@ class KhinsiderSoundtrackExtractor(AsynchronousExtractor):
def get_album_tracks(self, page): def get_album_tracks(self, page):
"""Collect url and metadata for all tracks of a soundtrack""" """Collect url and metadata for all tracks of a soundtrack"""
pos = page.find("Download all songs at once:") page = text.extract(page, '<table class="songlist">', '</table>')[0]
if pos == -1:
raise exception.NotFoundError("soundtrack")
page = text.extract(page, '<table align="center"', '</table>', pos)[0]
for num, url in enumerate(text.extract_iter( for num, url in enumerate(text.extract_iter(
page, '<td><a href="', '"'), 1): page, '<td><a href="', '"'), 1):
page = self.request(url, encoding="utf-8").text page = self.request(url, encoding="utf-8").text