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

[imgur] unescape album title + other fixes

Browse Source
This commit is contained in:
Mike Fährmann
2016-08-01 16:02:25 +02:00
parent db1738d451
commit c2c2e85da3
1 changed files with 9 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
gallery_dl/extractor/imgur.py
View File

@@ -10,11 +10,13 @@
from .common import Extractor, Message from .common import Extractor, Message
from .. import text from .. import text
from urllib.parse import urljoin
import os.path import os.path
class ImgurExtractor(Extractor): class ImgurAlbumExtractor(Extractor):
"""Extract albums from imgur"""
category = "imgur" category = "imgur"
subcategory = "album"
directory_fmt = ["{category}", "{album-key} - {title}"] directory_fmt = ["{category}", "{album-key} - {title}"]
filename_fmt = "{category}_{album-key}_{num:>03}_{name}.{extension}" filename_fmt = "{category}_{album-key}_{num:>03}_{name}.{extension}"
pattern = [r"(?:https?://)?(?:www\.)?imgur\.com/(?:a|gallery)/([^/?&#]+)"] pattern = [r"(?:https?://)?(?:www\.)?imgur\.com/(?:a|gallery)/([^/?&#]+)"]
@@ -45,12 +47,14 @@ class ImgurExtractor(Extractor):
"category": self.category, "category": self.category,
"album-key": self.album, "album-key": self.album,
} }
return text.extract_all(page, ( text.extract_all(page, (
('title', '<meta property="og:title" content="', '"'), ('title', '<meta property="og:title" content="', '"'),
('count', '"num_images":"', '"'), ('count', '"num_images":"', '"'),
('date' , '"datetime":"', ' '), ('date' , '"datetime":"', ' '),
('time' , '', '"'), ('time' , '', '"'),
), values=data)[0] ), values=data)
data["title"] = text.unescape(data["title"])
return data
def get_image_urls(self): def get_image_urls(self):
"""Yield urls of all images in this album""" """Yield urls of all images in this album"""
@@ -63,7 +67,7 @@ class ImgurExtractor(Extractor):
url, pos = text.extract(page, '<a href="', '"', pos) url, pos = text.extract(page, '<a href="', '"', pos)
if not url: if not url:
break break
yield "https:" + url yield urljoin("https:", url)
if pos == begin: if pos == begin:
return return
num += 1 num += 1