klbr/khoj
1
0
Fork 0
mirror of https://github.com/khoaliber/khoj.git synced 2026-03-07 21:29:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add try/except around image extraction step

Browse Source
This commit is contained in:
sabaimran
2023-11-04 19:27:18 -07:00
parent fdfab39942
commit 8c3d5a49da
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
src/khoj/processor/pdf/pdf_to_entries.py
View File

@@ -68,13 +68,16 @@ class PdfToEntries(TextToEntries):
with open(f"{tmp_file}", "wb") as f: with open(f"{tmp_file}", "wb") as f:
bytes = pdf_files[pdf_file] bytes = pdf_files[pdf_file]
f.write(bytes) f.write(bytes)
loader = PyMuPDFLoader(f"{tmp_file}", extract_images=True) try:
loader = PyMuPDFLoader(f"{tmp_file}", extract_images=True)
except ModuleNotFoundError:
loader = PyMuPDFLoader(f"{tmp_file}")
pdf_entries_per_file = [page.page_content for page in loader.load()] pdf_entries_per_file = [page.page_content for page in loader.load()]
entry_to_location_map += zip(pdf_entries_per_file, [pdf_file] * len(pdf_entries_per_file)) entry_to_location_map += zip(pdf_entries_per_file, [pdf_file] * len(pdf_entries_per_file))
entries.extend(pdf_entries_per_file) entries.extend(pdf_entries_per_file)
except Exception as e: except Exception as e:
logger.warning(f"Unable to process file: {pdf_file}. This file will not be indexed.") logger.warning(f"Unable to process file: {pdf_file}. This file will not be indexed.")
logger.warning(e) logger.warning(e, exc_info=True)
finally: finally:
if os.path.exists(f"{tmp_file}"): if os.path.exists(f"{tmp_file}"):
os.remove(f"{tmp_file}") os.remove(f"{tmp_file}")