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

[imagefap] deal with long filenames

Browse Source
This commit is contained in:
Mike Fährmann
2016-08-11 15:50:32 +02:00
parent 406add217c
commit fa14ef17ea
1 changed files with 21 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
gallery_dl/extractor/imagefap.py
View File

@@ -31,40 +31,44 @@ class ImagefapGalleryExtractor(Extractor):
self.gid = match.group(1) self.gid = match.group(1)
def items(self): def items(self):
imgurl_fmt = ("http://x.imagefapusercontent.com/u/{uploader}/" url = "http://www.imagefap.com/pictures/" + self.gid + "/"
"{gallery-id}/{image-id}/{filename}")
url = "http://www.imagefap.com/pictures/" + self.gid + "/?view=2"
page = self.request(url).text page = self.request(url).text
data = self.get_job_metadata(page) data = self.get_job_metadata(page)
yield Message.Version, 1 yield Message.Version, 1
yield Message.Directory, data yield Message.Directory, data
for image in self.get_images(page): for url, image in self.get_images(int(data["count"])):
data.update(image) data.update(image)
yield Message.Url, imgurl_fmt.format(**data), data yield Message.Url, url, data
def get_job_metadata(self, page): def get_job_metadata(self, page):
"""Collect metadata for extractor-job""" """Collect metadata for extractor-job"""
data = text.extract_all(page, ( data, pos = text.extract_all(page, (
("section" , '<meta name="description" content="', '"'), ("section" , '<meta name="description" content="', '"'),
("title" , '<title>Porn pics of ', ' (Page 1)</title>'), ("title" , '<title>Porn pics of ', ' (Page 1)</title>'),
("uploader", '>Uploaded by ', '</font>'), ("uploader", '>Uploaded by ', '</font>'),
("count" , ' 1 of ', ' pics"'), ("count" , ' 1 of ', ' pics"'),
), values={"category": self.category, "gallery-id": self.gid})[0] ), values={"category": self.category, "gallery-id": self.gid})
self.image_id = text.extract(page, 'id="img_ed_', '"', pos)[0]
data["title"] = text.unescape(data["title"]) data["title"] = text.unescape(data["title"])
return data return data
@staticmethod def get_images(self, count):
def get_images(page): """Collect image-urls and -metadata"""
"""Collect image-metadata"""
pos = 0
num = 0 num = 0
url = "http://www.imagefap.com/photo/" + self.image_id + "/"
params = {"gid": self.gid, "idx": 0, "partial": "true"}
while True: while True:
imgid, pos = text.extract(page, '<td id="', '"', pos) pos = 0
if not imgid: page = self.request(url, params=params).text
return for i in range(24):
name , pos = text.extract(page, '<i>', '</i>', pos) imgurl, pos = text.extract(page, '<a href="', '"', pos)
num += 1 num += 1
yield text.nameext_from_url(name, {"image-id": imgid, "num": num}) _, imgid, name = imgurl.rsplit("/", 2)
data = {"image-id": imgid, "num": num}
yield imgurl, text.nameext_from_url(name, data)
if num >= count:
return
params["idx"] += 24