AI/dify
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/langgenius/dify.git synced 2025-08-14 10:45:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

deal the external image when extract docx image (#5024)

Browse Source
This commit is contained in:
Jyong 2024-06-07 20:00:39 +08:00 committed by GitHub
parent ea0219a5d5
commit 3b60c28b3a
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
api/core/rag/extractor/word_extractor.py
View File

@ -76,6 +76,18 @@ class WordExtractor(BaseExtractor):
for rel in doc.part.rels.values():
if "image" in rel.target_ref:
image_count += 1
if rel.is_external:
url = rel.reltype
response = requests.get(url, stream=True)
if response.status_code == 200:
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())