Skip to content

GitLab

"vscode:/vscode.git/clone" did not exist on "c687fb83b20cfc09666902df4a90363645a262a9"
Unverified Commit 9f12c398 authored by Xiaomeng Zhao's avatar Xiaomeng Zhao Committed by GitHub
Browse files

Update pdf_parse_union_core_v2.py

parent 2c64ff3d
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 1 deletion
magic_pdf/pdf_parse_union_core_v2.py
View file @ 9f12c398
...@@ -178,7 +178,11 @@ def txt_spans_extract_v2(pdf_page, spans, all_bboxes, all_discarded_blocks, lang ...@@ -178,7 +178,11 @@ def txt_spans_extract_v2(pdf_page, spans, all_bboxes, all_discarded_blocks, lang
# text_blocks_raw = pdf_page.get_text('rawdict', flags=fitz.TEXT_PRESERVE_WHITESPACE | fitz.TEXT_MEDIABOX_CLIP)['blocks'] # text_blocks_raw = pdf_page.get_text('rawdict', flags=fitz.TEXT_PRESERVE_WHITESPACE | fitz.TEXT_MEDIABOX_CLIP)['blocks']
# cid用0xfffd表示，连字符不拆开 # cid用0xfffd表示，连字符不拆开
text_blocks_raw = pdf_page.get_text('rawdict', flags=fitz.TEXT_PRESERVE_LIGATURES | fitz.TEXT_PRESERVE_WHITESPACE | fitz.TEXT_MEDIABOX_CLIP)['blocks'] #text_blocks_raw = pdf_page.get_text('rawdict', flags=fitz.TEXT_PRESERVE_LIGATURES | fitz.TEXT_PRESERVE_WHITESPACE | fitz.TEXT_MEDIABOX_CLIP)['blocks']
# 自定义flags出现较多0xfffd，可能是pymupdf可以自行处理内置字典的pdf，不再使用
text_blocks_raw = pdf_page.get_text('rawdict', flags=fitz.TEXTFLAGS_TEXT)['blocks']
# text_blocks = pdf_page.get_text('dict', flags=fitz.TEXTFLAGS_TEXT)['blocks']
all_pymu_chars = [] all_pymu_chars = []
for block in text_blocks_raw: for block in text_blocks_raw:
for line in block['lines']: for line in block['lines']:
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment