[imagebam] fix extraction for certain galleries
This commit is contained in:
Mike Fährmann
@@ -8,91 +8,103 @@
|
||||
|
||||
"""Extract images from http://www.imagebam.com/"""
|
||||
|
||||
from .common import Extractor, AsynchronousExtractor, Message
|
||||
from .common import Extractor, Message
|
||||
from .. import text
|
||||
|
||||
|
||||
class ImagebamGalleryExtractor(AsynchronousExtractor):
|
||||
"""Extractor for image galleries from imagebam.com"""
|
||||
class ImagebamExtractor(Extractor):
|
||||
"""Base class for imagebam extractors"""
|
||||
category = "imagebam"
|
||||
subcategory = "gallery"
|
||||
directory_fmt = ["{category}", "{title} - {gallery_key}"]
|
||||
filename_fmt = "{num:>03}-{name}.{extension}"
|
||||
archive_fmt = "{gallery_key}_{image_id}"
|
||||
pattern = [r"(?:https?://)?(?:www\.)?imagebam\.com/gallery/([^/]+)"]
|
||||
test = [(("http://www.imagebam.com/"
|
||||
"gallery/adz2y0f9574bjpmonaismyrhtjgvey4o"), {
|
||||
"url": "fb01925129a1ff1941762eaa3a2783a66de6847f",
|
||||
"keyword": "2541078f61ce50714715e21757176dd69126f804",
|
||||
"content": "596e6bfa157f2c7169805d50075c2986549973a8",
|
||||
})]
|
||||
root = "http://www.imagebam.com"
|
||||
|
||||
def get_image_data(self, page_url, data):
|
||||
"""Fill 'data' and return image URL"""
|
||||
page = self.request(page_url).text
|
||||
image_url = text.extract(page, 'property="og:image" content="', '"')[0]
|
||||
data["extension"] = image_url.rpartition(".")[2]
|
||||
data["image_key"] = page_url.rpartition("/")[2]
|
||||
data["image_id"] = data["image_key"][6:]
|
||||
return image_url
|
||||
|
||||
|
||||
class ImagebamGalleryExtractor(ImagebamExtractor):
|
||||
"""Extractor for image galleries from imagebam.com"""
|
||||
subcategory = "gallery"
|
||||
directory_fmt = ["{category}", "{title} - {gallery_key}"]
|
||||
filename_fmt = "{num:>03}-{image_key}.{extension}"
|
||||
archive_fmt = "{gallery_key}_{image_key}"
|
||||
pattern = [r"(?:https?://)?(?:www\.)?imagebam\.com/gallery/([0-9a-z]+)"]
|
||||
test = [
|
||||
("http://www.imagebam.com/gallery/adz2y0f9574bjpmonaismyrhtjgvey4o", {
|
||||
"url": "fb01925129a1ff1941762eaa3a2783a66de6847f",
|
||||
"keyword": "9e25b8827474ac93c54855e798d60aa3cbecbd7a",
|
||||
"content": "596e6bfa157f2c7169805d50075c2986549973a8",
|
||||
}),
|
||||
("http://www.imagebam.com/gallery/gsl8teckymt4vbvx1stjkyk37j70va2c", {
|
||||
"url": "7d54178cecddfd46025cc9759f5b675fbb8f65af",
|
||||
"keyword": "7d7db9664061132be50aa0d98e9602e98eb581ce",
|
||||
}),
|
||||
]
|
||||
|
||||
def __init__(self, match):
|
||||
AsynchronousExtractor.__init__(self)
|
||||
self.gkey = match.group(1)
|
||||
ImagebamExtractor.__init__(self)
|
||||
self.gallery_key = match.group(1)
|
||||
|
||||
def items(self):
|
||||
data, url = self.get_job_metadata()
|
||||
url = "{}/gallery/{}".format(self.root, self.gallery_key)
|
||||
page = text.extract(
|
||||
self.request(url).text, "<fieldset>", "</fieldset>")[0]
|
||||
|
||||
data = self.get_metadata(page)
|
||||
imgs = self.get_image_pages(page)
|
||||
data["count"] = len(imgs)
|
||||
data["gallery_key"] = self.gallery_key
|
||||
|
||||
yield Message.Version, 1
|
||||
yield Message.Directory, data
|
||||
data["num"] = 0
|
||||
for image_url, image_id in self.get_images(url):
|
||||
data["image_id"] = image_id
|
||||
data["num"] += 1
|
||||
text.nameext_from_url(image_url, data)
|
||||
yield Message.Url, image_url, data.copy()
|
||||
for data["num"], page_url in enumerate(imgs, 1):
|
||||
image_url = self.get_image_data(page_url, data)
|
||||
yield Message.Url, image_url, data
|
||||
|
||||
def get_job_metadata(self):
|
||||
"""Collect metadata for extractor-job"""
|
||||
url = self.root + "/gallery/" + self.gkey
|
||||
page = self.request(url, encoding="utf-8").text
|
||||
data, pos = text.extract_all(page, (
|
||||
(None , "<img src='/img/icons/photos.png'", ""),
|
||||
("title" , "'> ", " <"),
|
||||
("count" , "'>", " images"),
|
||||
), values={"gallery_key": self.gkey})
|
||||
url, pos = text.extract(
|
||||
page, "<a href='http://www.imagebam.com", "'", pos)
|
||||
return data, url
|
||||
@staticmethod
|
||||
def get_metadata(page):
|
||||
"""Return gallery metadata"""
|
||||
return text.extract_all(page, (
|
||||
("title" , "'> ", " <span "),
|
||||
(None , "'>", "</span>"),
|
||||
("description", ":#FCFCFC;'>", "</div>"),
|
||||
))[0]
|
||||
|
||||
def get_images(self, url):
|
||||
"""Yield all image-urls and -ids for a gallery"""
|
||||
done = False
|
||||
while not done:
|
||||
page = self.request(self.root + url).text
|
||||
pos = text.extract(
|
||||
page, 'class="btn btn-default" title="Next">', ''
|
||||
)[1]
|
||||
if pos == 0:
|
||||
done = True
|
||||
else:
|
||||
url, pos = text.extract(page, ' href="', '"', pos-70)
|
||||
image_id , pos = text.extract(page, 'class="image" id="', '"', pos)
|
||||
image_url, pos = text.extract(page, 'src="', '"', pos)
|
||||
yield image_url, image_id
|
||||
@staticmethod
|
||||
def get_image_pages(page):
|
||||
"""Return a list of all image pages"""
|
||||
return list(text.extract_iter(page, "<a href='", "'"))
|
||||
|
||||
|
||||
class ImagebamImageExtractor(Extractor):
|
||||
class ImagebamImageExtractor(ImagebamExtractor):
|
||||
"""Extractor for single images from imagebam.com"""
|
||||
category = "imagebam"
|
||||
subcategory = "image"
|
||||
archive_fmt = "{token}"
|
||||
pattern = [r"(?:https?://)?(?:www\.)?imagebam\.com/image/([0-9a-f]{15})"]
|
||||
test = [("http://www.imagebam.com/image/94d56c502511890", {
|
||||
"url": "b384893c35a01a09c58018db71ddc4cf2480be95",
|
||||
"keyword": "1c7bc3f31ba248d65e085eb82d16f8e2156ec102",
|
||||
"content": "0c8768055e4e20e7c7259608b67799171b691140",
|
||||
})]
|
||||
filename_fmt = "{image_key}.{extension}"
|
||||
archive_fmt = "{image_key}"
|
||||
pattern = [r"(?:https?://)?(?:\w+\.)?imagebam\.com"
|
||||
r"/(?:image/|(?:[0-9a-f]{2}/){3})([0-9a-f]+)"]
|
||||
test = [
|
||||
("http://www.imagebam.com/image/94d56c502511890", {
|
||||
"url": "b384893c35a01a09c58018db71ddc4cf2480be95",
|
||||
"keyword": "4263d4840007524129792b8587a562b5d20c2687",
|
||||
"content": "0c8768055e4e20e7c7259608b67799171b691140",
|
||||
}),
|
||||
("http://images3.imagebam.com/1d/8c/44/94d56c502511890.png", None),
|
||||
]
|
||||
|
||||
def __init__(self, match):
|
||||
Extractor.__init__(self)
|
||||
self.token = match.group(1)
|
||||
ImagebamExtractor.__init__(self)
|
||||
self.image_key = match.group(1)
|
||||
|
||||
def items(self):
|
||||
page = self.request("http://www.imagebam.com/image/" + self.token).text
|
||||
iurl = text.extract(page, 'property="og:image" content="', '"')[0]
|
||||
data = text.nameext_from_url(iurl, {"token": self.token})
|
||||
page_url = "{}/image/{}".format(self.root, self.image_key)
|
||||
data = {}
|
||||
image_url = self.get_image_data(page_url, data)
|
||||
yield Message.Version, 1
|
||||
yield Message.Directory, data
|
||||
yield Message.Url, iurl, data
|
||||
yield Message.Url, image_url, data
|
||||
|
||||
Reference in New Issue
Block a user