[fantia] prevent '.html' file downloads
This commit is contained in:
@@ -56,6 +56,7 @@ class FantiaExtractor(Extractor):
|
|||||||
"%s#post-content-id-%s", content["visible_status"],
|
"%s#post-content-id-%s", content["visible_status"],
|
||||||
post["post_url"], content["id"])
|
post["post_url"], content["id"])
|
||||||
|
|
||||||
|
post["_http_validate"] = self._validate_response
|
||||||
for file in files:
|
for file in files:
|
||||||
post.update(file)
|
post.update(file)
|
||||||
post["num"] += 1
|
post["num"] += 1
|
||||||
@@ -90,6 +91,10 @@ class FantiaExtractor(Extractor):
|
|||||||
self.headers["X-CSRF-Token"] = text.extr(
|
self.headers["X-CSRF-Token"] = text.extr(
|
||||||
page, 'name="csrf-token" content="', '"')
|
page, 'name="csrf-token" content="', '"')
|
||||||
|
|
||||||
|
def _validate_response(self, response):
|
||||||
|
return not response.history or not response.headers.get(
|
||||||
|
"content-type", "").startswith("text/html")
|
||||||
|
|
||||||
def _get_post_data(self, post_id):
|
def _get_post_data(self, post_id):
|
||||||
"""Fetch and process post data"""
|
"""Fetch and process post data"""
|
||||||
url = self.root+"/api/v1/posts/"+post_id
|
url = self.root+"/api/v1/posts/"+post_id
|
||||||
|
|||||||
Reference in New Issue
Block a user