def inspect(file: Union[str, bytes, Path]) -> PdfRedactionsDict:
"""
Inspect a file for bad redactions and return a Dict with their info
:file: The PDF to process, as bytes if you have the file in memory (useful
if it's coming from the network), as a unicode string if you know the
path to the file on your local disk, or as a pathlib.Path object.
:return: A dict with the bad redaction information. If no bad redactions
are found, returns an empty dict.
"""
if type(file) == bytes:
pdf = Document(stream=file, filetype="pdf")
elif type(file) == str and file.startswith("https://"):
r = requests.get(file, timeout=10)
r.raise_for_status()
pdf = Document(stream=r.content, filetype="pdf")
else:
# str filepath or Pathlib Path
pdf = Document(file)
bad_redactions = {}
for page_number, page in enumerate(pdf, start=1):
redactions = get_bad_redactions(page)
if redactions:
bad_redactions[page_number] = redactions
pdf.close()
bad_redactions = check_if_all_dates(bad_redactions)
return bad_redactions
for name in names_list:
print(f"Parsing: {name}")
word_in_pages = []
results.write(f"{name} ")
for page in range(start, end):
lines = unescape(doc[page].getText("html")).split("\n")
for line in lines:
item = line.replace("\t", " ")
bs = BeautifulSoup(item, "html.parser")
if bs.p is not None:
if name.title() in str(bs.p.text) and str(
bs.p["style"]).find("top:84pt") == -1:
font_index = str(bs.p.span["style"]).find("font-size")
font_size = str(bs.p.span["style"][font_index:]).lstrip(
"font-size:")[:2].rstrip("p").rstrip(".")
string_to_write = str(page + page_delta)
if int(font_size) < font_standard:
string_to_write += "n"
if string_to_write in word_in_pages:
continue
else:
print("\t'{}' found in page {}".format(name, page))
word_in_pages.append(string_to_write)
string_to_write = ""
merged_pages = merge_results(word_in_pages)
write_to_file(merged_pages, results)
results.write("\n")
results.close()
doc.close()
results_cleaner(results_file)