def search_outline_in_pages(self, pattern, page_range=None, size='fontname', verbose=False, show_matched=False) -> list:
'''
return a list of pages number in tuples that contains pattern
'''
print('search by page!')
# print(f'pattern: {pattern}')
pages = set()
matched_pattern = []
with _by_pdfplumber(self.pdf_obj) as pdf:
if not page_range:
page_range = pdf.pages
else:
page_range = [pdf.pages[p] for p in page_range]
for page in page_range:
p = page.page_number - 1
# if verbose: print(f'searching p.{p}')
try:
title_alike_txts = get_title_liked_txt(page, size=size)
except KeyError:
logging.warning('Non textual page')
continue
for txt in title_alike_txts:
if search_pattern_from_txt(txt, pattern):
pages.add(p)
matched_pattern.append(txt)
if verbose: print(f'with pattern: found {txt} on p.{p}!')
consecutive_pages = [tuple(li) for li in consecutive_int_list(unique(pages))]
if show_matched:
return consecutive_pages, matched_pattern
return consecutive_pages
def _get_page_by_page_title_search(pdfplumber_obj, keywords_pattern=None, verbose=False) -> list:
'''
return a list of pages that contains title_pattern
'''
if verbose:
print(f'searching by page!')
if keywords_pattern is None:
keywords_pattern = r'^(?!.*internal)(?=.*report).*auditor.*$'
pages = []
for p, page in enumerate(pdfplumber_obj.pages):
if verbose:
print(f'searching p.{p}')
try:
title_alike_txts = get_title_liked_txt(page)
except KeyError:
logging.warning('Non textual page')
continue
for txt in title_alike_txts:
if search_pattern_from_txt(txt, keywords_pattern):
pages.append(p)
if verbose: print(f'with pattern: found {txt}on p.{p}!')
# consecutive_pages = pages
consecutive_pages = [tuple(li) for li in consecutive_int_list(unique(pages))]
# consecutive_pages = sorted(flatten([li for li in consecutive_int_list(list(set(pages))) if len(li) > 1]))
# consecutive_pages = [tuple(li) for li in consecutive_int_list(list(set(pages))) if len(li) > 1]
return consecutive_pages
def _get_page_by_outline(toc, title_pattern, to_page=True) -> list:
'''
return a list of matched title pattern page range
'''
# print('from outline')
# if to_page:
# return [page_range[-1] for outline, page_range in toc.items() if re.search(title_pattern, outline, flags=re.IGNORECASE)]
# else:
# return [page_range for outline, page_range in toc.items() if re.search(title_pattern, outline, flags=re.IGNORECASE)]
# return [list(range(page_range[0], page_range[1] + 1)) for outline, page_range in toc.items() if re.search(title_pattern, outline, flags=re.IGNORECASE)]
pages = flatten([list(range(page_range[0], page_range[1] + 1)) for outline, page_range in toc.items() if re.search(title_pattern, outline, flags=re.IGNORECASE)])
consecutive_pages = [tuple(li) for li in consecutive_int_list(unique(pages))]
return consecutive_pages
def search_outline_in_toc(self, pattern) -> list:
'''
return a list of matched title pattern page range
'''
print('search by toc!')
pages = []
for outline, _page_range in self.toc.items():
if re.search(pattern, outline, flags=re.IGNORECASE):
from_page, to_page = _page_range
page_range = list(range(from_page, to_page + 1))
pages.append(page_range)
pages = flatten(pages)
consecutive_pages = [tuple(li) for li in consecutive_int_list(unique(pages))]
return consecutive_pages
def search_outline(self, regex: Pattern, scope=None) -> list:
pdf = self.pb_pdf
pages = scope or pdf.pages
matched_page_nums = set()
for p in pages:
page = Page.create(p)
if not page or page.df_feature_text.empty:
continue
self.logger.debug(f'searching page {page.page_number}...')
if any(page.df_feature_text.text.str.contains(regex, flags=re.IGNORECASE)):
matched_page_nums.add(page.page_number)
matched_page_num = max(consecutive_int_list(sorted(matched_page_nums)), key=len, default=None)
if matched_page_num is None:
return []
page_range = min(matched_page_num), max(matched_page_num)
scope = 'Local' if scope else 'Global'
return [Outline(f'{scope} search pattern: {regex}', page_range, self.pb_pdf)]