Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 10:42:34 +01:00
Code Issues Releases Wiki Activity

[hentai2read] fix parsing for new page layout

Browse Source
This commit is contained in:
Mike Fährmann 2016-04-20 08:25:06 +02:00
parent 871f4c8a48
commit 1416e7f6f7
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
1 changed files with 5 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
gallery_dl/extractor/hentai2read.py
View File

@ -39,8 +39,8 @@ class Hentai2ReadMangaExtractor(Extractor):
def get_chapters(self):
"""Return a list of all chapter urls"""
page = self.request("http://hentai2read.com/" + self.url_title).text
page = text.extract(page, '<div class="text">\n<ul>', '</ul>')[0]
needle = '<a href="'
page = text.extract(page, '<ul class="nav-chapters remove-margin-b">', '</ul>\n</div>')[0]
needle = '<li>\n<a href="'
return reversed(list(
text.extract_iter(page, needle, '"')
))
@ -68,8 +68,9 @@ class Hentai2ReadChapterExtractor(Extractor):
data = self.get_job_metadata(page, images)
yield Message.Version, 1
yield Message.Directory, data
for num, url in enumerate(images, 1):
for num, part in enumerate(images, 1):
data["num"] = num
url = "http://hentaicdn.com/hentai" + part
yield Message.Url, url, text.nameext_from_url(url, data)
def get_job_metadata(self, page, images):
@ -90,5 +91,5 @@ class Hentai2ReadChapterExtractor(Extractor):
@staticmethod
def get_image_urls(page):
"""Extract and return a list of all image-urls"""
images = text.extract(page, "var wpm_mng_rdr_img_lst = ", ";")[0]
images = text.extract(page, "var rff_imageList = ", ";")[0]
return json.loads(images)