diff options
Diffstat (limited to 'gallery_dl/extractor/imagefap.py')
| -rw-r--r-- | gallery_dl/extractor/imagefap.py | 37 |
1 files changed, 18 insertions, 19 deletions
diff --git a/gallery_dl/extractor/imagefap.py b/gallery_dl/extractor/imagefap.py index 1efbbf0..497f1ef 100644 --- a/gallery_dl/extractor/imagefap.py +++ b/gallery_dl/extractor/imagefap.py @@ -9,8 +9,7 @@ """Extractors for https://www.imagefap.com/""" from .common import Extractor, Message -from .. import text, exception -import json +from .. import text, util, exception BASE_PATTERN = r"(?:https?://)?(?:www\.|beta\.)?imagefap\.com" @@ -47,7 +46,7 @@ class ImagefapGalleryExtractor(ImagefapExtractor): pattern = BASE_PATTERN + r"/(?:gallery\.php\?gid=|gallery/|pictures/)(\d+)" test = ( - ("https://www.imagefap.com/pictures/7102714", { + ("https://www.imagefap.com/gallery/7102714", { "pattern": r"https://cdnh?\.imagefap\.com" r"/images/full/\d+/\d+/\d+\.jpg", "keyword": "2ba96e84c2952c4750e9fa94a3f2b1f965cec2f3", @@ -68,6 +67,7 @@ class ImagefapGalleryExtractor(ImagefapExtractor): }, "count": 44, }), + ("https://www.imagefap.com/pictures/7102714"), ("https://www.imagefap.com/gallery.php?gid=7102714"), ("https://beta.imagefap.com/gallery.php?gid=7102714"), ) @@ -78,7 +78,7 @@ class ImagefapGalleryExtractor(ImagefapExtractor): self.image_id = "" def items(self): - url = "{}/pictures/{}/".format(self.root, self.gid) + url = "{}/gallery/{}".format(self.root, self.gid) page = self.request(url).text data = self.get_job_metadata(page) yield Message.Directory, data @@ -88,22 +88,21 @@ class ImagefapGalleryExtractor(ImagefapExtractor): def get_job_metadata(self, page): """Collect metadata for extractor-job""" - descr, pos = text.extract( - page, '<meta name="description" content="Browse ', '"') - count, pos = text.extract(page, ' 1 of ', ' pics"', pos) - self.image_id = text.extract(page, 'id="img_ed_', '"', pos)[0] - - title, _, descr = descr.partition(" porn picture gallery by ") - uploader, _, tags = descr.partition(" to see hottest ") - self._count = text.parse_int(count) - return { + extr = text.extract_from(page) + + data = { "gallery_id": text.parse_int(self.gid), - "title": text.unescape(title), - "uploader": uploader, - "tags": tags[:-11].split(", "), - "count": self._count, + "tags": extr('name="keywords" content="', '"').split(", "), + "uploader": extr("porn picture gallery by ", " to see hottest"), + "title": text.unescape(extr("<title>", "<")), + "count": text.parse_int(extr(' 1 of ', ' pics"')), } + self.image_id = extr('id="img_ed_', '"') + self._count = data["count"] + + return data + def get_images(self): """Collect image-urls and -metadata""" url = "{}/photo/{}/".format(self.root, self.image_id) @@ -128,7 +127,7 @@ class ImagefapGalleryExtractor(ImagefapExtractor): data["image_id"] = text.parse_int(data["filename"]) yield image_url, data - if cnt < 24 and num >= total: + if not cnt or cnt < 24 and num >= total: return params["idx"] += cnt @@ -173,7 +172,7 @@ class ImagefapImageExtractor(ImagefapExtractor): page, 'id="imageid_input" value="', '"', pos) gallery_id, pos = text.extract( page, 'id="galleryid_input" value="', '"', pos) - info = json.loads(info) + info = util.json_loads(info) url = info["contentUrl"] return url, text.nameext_from_url(url, { |