Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
wangsen
MinerU
Commits
a5e22396
Commit
a5e22396
authored
Apr 26, 2024
by
赵小蒙
Browse files
delete svgs check
parent
dc45a0f2
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
2 additions
and
2 deletions
+2
-2
magic_pdf/filter/pdf_meta_scan.py
magic_pdf/filter/pdf_meta_scan.py
+2
-2
No files found.
magic_pdf/filter/pdf_meta_scan.py
View file @
a5e22396
...
@@ -305,7 +305,7 @@ def pdf_meta_scan(pdf_bytes: bytes):
...
@@ -305,7 +305,7 @@ def pdf_meta_scan(pdf_bytes: bytes):
page_width_pts
,
page_height_pts
=
get_pdf_page_size_pts
(
doc
)
page_width_pts
,
page_height_pts
=
get_pdf_page_size_pts
(
doc
)
# logger.info(f"page_width_pts: {page_width_pts}, page_height_pts: {page_height_pts}")
# logger.info(f"page_width_pts: {page_width_pts}, page_height_pts: {page_height_pts}")
svgs_per_page
=
get_svgs_per_page
(
doc
)
#
svgs_per_page = get_svgs_per_page(doc)
# logger.info(f"svgs_per_page: {svgs_per_page}")
# logger.info(f"svgs_per_page: {svgs_per_page}")
imgs_per_page
=
get_imgs_per_page
(
doc
)
imgs_per_page
=
get_imgs_per_page
(
doc
)
# logger.info(f"imgs_per_page: {imgs_per_page}")
# logger.info(f"imgs_per_page: {imgs_per_page}")
...
@@ -331,7 +331,7 @@ def pdf_meta_scan(pdf_bytes: bytes):
...
@@ -331,7 +331,7 @@ def pdf_meta_scan(pdf_bytes: bytes):
"text_len_per_page"
:
text_len_per_page
,
"text_len_per_page"
:
text_len_per_page
,
"text_layout_per_page"
:
text_layout_per_page
,
"text_layout_per_page"
:
text_layout_per_page
,
"text_language"
:
text_language
,
"text_language"
:
text_language
,
"svgs_per_page"
:
svgs_per_page
,
#
"svgs_per_page": svgs_per_page,
"imgs_per_page"
:
imgs_per_page
,
# 增加每页img数量list
"imgs_per_page"
:
imgs_per_page
,
# 增加每页img数量list
"junk_img_bojids"
:
junk_img_bojids
,
# 增加垃圾图片的bojid list
"junk_img_bojids"
:
junk_img_bojids
,
# 增加垃圾图片的bojid list
"metadata"
:
doc
.
metadata
"metadata"
:
doc
.
metadata
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment