Mirrors/gallery-dl
1
0
Fork 0
mirror of https://github.com/mikf/gallery-dl.git synced 2024-11-22 02:32:33 +01:00
Code Issues Releases Wiki Activity

[pixiv] get ugoira frame extension from 'meta_single_page' (#6056)

Browse Source 
saves 1-3 HEAD requests
This commit is contained in:
Mike Fährmann 2024-10-31 19:47:05 +01:00
parent f79e57b71e
commit b321696182
No known key found for this signature in database
GPG Key ID: 5680CA389D365A88
1 changed files with 27 additions and 19 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

46
gallery_dl/extractor/pixiv.py
View File

@ -33,6 +33,7 @@ class PixivExtractor(Extractor):
def _init(self):
self.api = PixivAppAPI(self)
self.load_ugoira = self.config("ugoira", True)
self.load_ugoira_original = (self.load_ugoira == "original")
self.max_posts = self.config("max-posts", 0)
self.sanity_workaround = self.config("sanity", True)
self.meta_user = self.config("metadata")
@ -131,7 +132,7 @@ class PixivExtractor(Extractor):
elif self.load_ugoira:
try:
return self._extract_ugoira(work)
return self._extract_ugoira(work, url)
except Exception as exc:
self.log.warning(
"%s: Unable to retrieve Ugoira metatdata (%s - %s)",
@ -139,28 +140,33 @@ class PixivExtractor(Extractor):
return ()
def _extract_ugoira(self, work):
def _extract_ugoira(self, work, img_url):
ugoira = self.api.ugoira_metadata(work["id"])
url = ugoira["zip_urls"]["medium"]
work["_ugoira_frame_data"] = work["frames"] = frames = ugoira["frames"]
work["date_url"] = self._date_from_url(url)
work["_ugoira_original"] = self.load_ugoira_original
work["_http_adjust_extension"] = False
if self.load_ugoira == "original":
work["_ugoira_original"] = True
base, sep, _ = url.rpartition("_ugoira")
base = base.replace("/img-zip-ugoira/", "/img-original/", 1) + sep
if self.load_ugoira_original:
work["date_url"] = self._date_from_url(img_url)
for ext in ("jpg", "png", "gif"):
try:
url = "{}0.{}".format(base, ext)
self.request(url, method="HEAD")
break
except exception.HttpError:
pass
base, sep, ext = img_url.rpartition("_ugoira0.")
if sep:
base += "_ugoira"
else:
self.log.warning(
"Unable to find Ugoira frame URLs (%s)", work["id"])
base, sep, _ = img_url.rpartition("_ugoira")
base = base.replace(
"/img-zip-ugoira/", "/img-original/", 1) + sep
for ext in ("jpg", "png", "gif"):
try:
url = "{}0.{}".format(base, ext)
self.request(url, method="HEAD")
break
except exception.HttpError:
pass
else:
self.log.warning(
"Unable to find Ugoira frame URLs (%s)", work["id"])
return [
{
@ -170,9 +176,11 @@ class PixivExtractor(Extractor):
}
for num in range(len(frames))
]
else:
work["_ugoira_original"] = False
url = url.replace("_ugoira600x600", "_ugoira1920x1080", 1)
zip_url = ugoira["zip_urls"]["medium"]
work["date_url"] = self._date_from_url(zip_url)
url = zip_url.replace("_ugoira600x600", "_ugoira1920x1080", 1)
return ({"url": url},)
def _request_ajax(self, endpoint):