diff options
| author | Bryan Newbold <bnewbold@archive.org> | 2020-06-25 23:06:36 -0700 |
|---|---|---|
| committer | Bryan Newbold <bnewbold@archive.org> | 2020-06-25 23:06:36 -0700 |
| commit | fa25698620f54207423c3da40ae1bca567b598fa (patch) | |
| tree | e18d90d9561f0ee590e23867be738f7e3e7495bf | |
| parent | a4de486bdd28b71562ae65d7ce6c8c741e5056b3 (diff) | |
| download | sandcrawler-fa25698620f54207423c3da40ae1bca567b598fa.tar.gz sandcrawler-fa25698620f54207423c3da40ae1bca567b598fa.zip | |
pdfextract: attributerror with text extraction
| -rw-r--r-- | python/sandcrawler/pdfextract.py | 16 |
1 files changed, 12 insertions, 4 deletions
diff --git a/python/sandcrawler/pdfextract.py b/python/sandcrawler/pdfextract.py index 98d6861..921c883 100644 --- a/python/sandcrawler/pdfextract.py +++ b/python/sandcrawler/pdfextract.py @@ -194,10 +194,18 @@ def process_pdf(blob: bytes, thumb_size=(180,300), thumb_type="JPEG") -> PdfExtr print(str(e), file=sys.stderr) page0_thumbnail = None - full_text = page0.text() - for n in range(1, pdf.pages): - pageN = pdf.create_page(n) - full_text += pageN.text() + try: + full_text = page0.text() + for n in range(1, pdf.pages): + pageN = pdf.create_page(n) + full_text += pageN.text() + except AttributeError as e: + return PdfExtractResult( + sha1hex=sha1hex, + status='parse-error', + error_msg=str(e), + file_meta=file_meta, + ) # Kafka message size limit; cap at about 1 MByte if len(full_text)> 1000000: |