1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 10:42:34 +01:00

[imgur] fix parsing

This commit is contained in:
Mike Fährmann 2015-11-11 21:44:00 +01:00
parent 129ca282e4
commit 4427734b70
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88

View File

@ -41,8 +41,7 @@ class ImgurExtractor(Extractor):
def get_job_metadata(self, page): def get_job_metadata(self, page):
"""Collect metadata for extractor-job""" """Collect metadata for extractor-job"""
_ , pos = text.extract(page, '<h1 ', '>') title, _ = text.extract(page, '<meta property="og:title" content="', '"')
title, pos = text.extract(page, '', '</h1>', pos)
return { return {
"category": info["category"], "category": info["category"],
"album-key": self.album, "album-key": self.album,
@ -56,10 +55,10 @@ class ImgurExtractor(Extractor):
pos = 0 pos = 0
num = 0 num = 0
while True: while True:
url , pos = text.extract(page, 'property="og:image" content="', '"', pos) url , pos = text.extract(page, 'property="og:image" content="', '"', pos)
if not url: if not url:
return images return images
width , pos = text.extract(page, 'property="og:image:width" content="', '"', pos) width , pos = text.extract(page, 'property="og:image:width" content="', '"', pos)
height, pos = text.extract(page, 'property="og:image:height" content="', '"', pos) height, pos = text.extract(page, 'property="og:image:height" content="', '"', pos)
name = os.path.splitext(text.filename_from_url(url)) name = os.path.splitext(text.filename_from_url(url))
num += 1 num += 1