blade
/
dc-ml-emea-ar
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

if fail to get text by pdf to html API, then try to get text by pymupdf.

This commit is contained in:
Blade He 2025-01-15 18:36:02 -06:00
parent ace0ac2674
commit acc30d4b72
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
core/page_filter.py
View File

@ -40,6 +40,9 @@ class FilterPages:
page_text_dict = {}
if self.apply_pdf2html:
page_text_dict = get_pdf_pages_by_html(self.pdf_file, pdf_info_type="pdf_path")
if len(page_text_dict.keys()) == 0:
pdf_util = PDFUtil(self.pdf_file)
success, text, page_text_dict = pdf_util.extract_text()
else:
pdf_util = PDFUtil(self.pdf_file)
success, text, page_text_dict = pdf_util.extract_text()

2
main.py
View File

@ -1165,7 +1165,7 @@ if __name__ == "__main__":
"554851189",
"555377021",
"555654388"]
# special_doc_id_list: list = ["539790009", "542301117"]
# special_doc_id_list: list = ["542301117"]
pdf_folder:str = r"/data/aus_prospectus/pdf/"
output_pdf_text_folder:str = r"/data/aus_prospectus/output/pdf_text/"
output_extract_data_child_folder:str = r"/data/aus_prospectus/output/extract_data/docs/"