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

[imgur] fix image url retrieval

Browse Source
This commit is contained in:
Mike Fährmann
2016-10-07 00:13:51 +02:00
parent bf8d88499a
commit 8c8ad08e28
1 changed files with 18 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
gallery_dl/extractor/imgur.py
View File

@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright 2015 Mike Fährmann # Copyright 2015, 2016 Mike Fährmann
# #
# This program is free software; you can redistribute it and/or modify # This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as # it under the terms of the GNU General Public License version 2 as
@@ -9,20 +9,18 @@
"""Extract images from albums at https://imgur.com/""" """Extract images from albums at https://imgur.com/"""
from .common import Extractor, Message from .common import Extractor, Message
from .. import text from .. import text, exception
from urllib.parse import urljoin
import os.path
class ImgurAlbumExtractor(Extractor): class ImgurAlbumExtractor(Extractor):
"""Extractor for image albums from imgur.com""" """Extractor for image albums from imgur.com"""
category = "imgur" category = "imgur"
subcategory = "album" 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}_{hash}{ext}"
pattern = [r"(?:https?://)?(?:www\.)?imgur\.com/(?:a|gallery)/([^/?&#]+)"] pattern = [r"(?:https?://)?(?:www\.)?imgur\.com/(?:a|gallery)/([^/?&#]+)"]
test = [("https://imgur.com/a/TcBmP", { test = [("https://imgur.com/a/TcBmP", {
"url": "ce3552f550a5b5316bd9c7ae02e21e39f30c0563", "url": "ce3552f550a5b5316bd9c7ae02e21e39f30c0563",
"keyword": "c76bbf86f8f114cdaadab396c0ea4acf47aa44eb", "keyword": "8301572a22c139b5e0704ccaf2bcf49a111e2384",
})] })]
def __init__(self, match): def __init__(self, match):
@@ -30,15 +28,15 @@ class ImgurAlbumExtractor(Extractor):
self.album = match.group(1) self.album = match.group(1)
def items(self): def items(self):
imgs = self.get_images()
data = self.get_job_metadata() data = self.get_job_metadata()
yield Message.Version, 1 yield Message.Version, 1
yield Message.Directory, data yield Message.Directory, data
for num, url in enumerate(self.get_image_urls(), 1): for num, image in enumerate(imgs, 1):
name, ext = os.path.splitext(url[20:]) image["num"] = num
data["num"] = num image.update(data)
data["name"] = name url = "https://i.imgur.com/" + image["hash"] + image["ext"]
data["extension"] = ext[1:] yield Message.Url, url, image
yield Message.Url, url, data
def get_job_metadata(self): def get_job_metadata(self):
"""Collect metadata for extractor-job""" """Collect metadata for extractor-job"""
@@ -46,24 +44,15 @@ class ImgurAlbumExtractor(Extractor):
data = text.extract_all(page, ( data = text.extract_all(page, (
('title', '<meta property="og:title" content="', '"'), ('title', '<meta property="og:title" content="', '"'),
('count', '"num_images":"', '"'), ('count', '"num_images":"', '"'),
('date' , '"datetime":"', ' '),
('time' , '', '"'),
), values={"album-key": self.album})[0] ), values={"album-key": self.album})[0]
data["title"] = text.unescape(data["title"]) data["title"] = text.unescape(data["title"])
return data return data
def get_image_urls(self): def get_images(self):
"""Yield urls of all images in this album""" """Return a list of all images in this album"""
num = 0 url = ("https://imgur.com/ajaxalbums/getimages/"
while True: + self.album + "/hit.json")
url = "https://imgur.com/a/{}/all/page/{}?scrolled".format(self.album, num) data = self.request(url).json()["data"]
page = self.request(url).text if not data:
pos = begin = text.extract(page, '<div class="posts">', '')[1] raise exception.NotFoundError("album")
while True: return data["images"]
url, pos = text.extract(page, '<a href="', '"', pos)
if not url:
break
yield urljoin("https:", url)
if pos == begin:
return
num += 1