1
0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 18:53:21 +01:00

[pixhost] add extractor

This commit is contained in:
Mike Fährmann 2016-11-09 12:03:14 +01:00
parent 07e9e2c4f1
commit 88193718e8
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88

View File

@ -20,6 +20,7 @@ class ImagehostImageExtractor(Extractor):
https = False
method = "post"
params = "simple"
cookies = None
def __init__(self, match):
Extractor.__init__(self)
@ -42,7 +43,8 @@ class ImagehostImageExtractor(Extractor):
self.method = "get"
def items(self):
page = self.request(self.url, method=self.method, data=self.params).text
page = self.request(self.url, method=self.method, data=self.params,
cookies=self.cookies).text
url, filename = self.get_info(page)
data = text.nameext_from_url(filename, {"token": self.token})
if self.https and url.startswith("http:"):
@ -249,6 +251,21 @@ class ImgtrexImageExtractor(ImagehostImageExtractor):
return url, filename
class PixhostImageExtractor(ImagehostImageExtractor):
"""Extractor for single images from pixhost.org"""
category = "pixhost"
pattern = [(r"(?:https?://)?((?:www\.)?pixhost\.org/show/"
r"\d+/(\d+)_[^/]+)")]
params = None
cookies = {"pixhostads": "1", "pixhosttest": "1"}
def get_info(self, page):
filename, pos = text.extract(page, '<div id="text">\n<h2>', '</h2>')
url , pos = text.extract(page, '<img id="show_image" src="', '"', pos)
pos = filename.find("_")
return url, filename[pos+1:] if pos != -1 else url
class TurboimagehostImageExtractor(ImagehostImageExtractor):
"""Extractor for single images from turboimagehost.com"""
category = "turboimagehost"