|
|
@@ -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']
|
|
|
|
|
|
# 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 = []
|
|
|
for block in text_blocks_raw:
|
|
|
for line in block['lines']:
|
Xiaomeng Zhao