mirror of
https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git
synced 2025-08-14 10:35:51 +08:00
deal the external image when extract docx image (#5024)
This commit is contained in:
parent
ea0219a5d5
commit
3b60c28b3a
@ -76,13 +76,25 @@ class WordExtractor(BaseExtractor):
|
|||||||
for rel in doc.part.rels.values():
|
for rel in doc.part.rels.values():
|
||||||
if "image" in rel.target_ref:
|
if "image" in rel.target_ref:
|
||||||
image_count += 1
|
image_count += 1
|
||||||
image_ext = rel.target_ref.split('.')[-1]
|
if rel.is_external:
|
||||||
# user uuid as file name
|
url = rel.reltype
|
||||||
file_uuid = str(uuid.uuid4())
|
response = requests.get(url, stream=True)
|
||||||
file_key = 'image_files/' + self.tenant_id + '/' + file_uuid + '.' + image_ext
|
if response.status_code == 200:
|
||||||
mime_type, _ = mimetypes.guess_type(file_key)
|
image_ext = mimetypes.guess_extension(response.headers['Content-Type'])
|
||||||
|
file_uuid = str(uuid.uuid4())
|
||||||
|
file_key = 'image_files/' + self.tenant_id + '/' + file_uuid + '.' + image_ext
|
||||||
|
mime_type, _ = mimetypes.guess_type(file_key)
|
||||||
|
storage.save(file_key, response.content)
|
||||||
|
else:
|
||||||
|
continue
|
||||||
|
else:
|
||||||
|
image_ext = rel.target_ref.split('.')[-1]
|
||||||
|
# user uuid as file name
|
||||||
|
file_uuid = str(uuid.uuid4())
|
||||||
|
file_key = 'image_files/' + self.tenant_id + '/' + file_uuid + '.' + image_ext
|
||||||
|
mime_type, _ = mimetypes.guess_type(file_key)
|
||||||
|
|
||||||
storage.save(file_key, rel.target_part.blob)
|
storage.save(file_key, rel.target_part.blob)
|
||||||
# save file to db
|
# save file to db
|
||||||
config = current_app.config
|
config = current_app.config
|
||||||
upload_file = UploadFile(
|
upload_file = UploadFile(
|
||||||
|
Loading…
x
Reference in New Issue
Block a user