xenofem/dlibrary
1
0
Fork 0
Code Issues 3 Pull requests Packages Projects Releases Wiki Activity

also check whether PDFs have text alongside images

Browse source
This commit is contained in:
xenofem 2024-03-02 18:27:15 -05:00
parent c042163e85
commit 7535cb6162
1 changed files with 8 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
dlibrary/dlibrary.py
View file

@ -437,17 +437,21 @@ class Collator:
return self.collate_from_paths(srcs_matching_language) return self.collate_from_paths(srcs_matching_language)
def is_single_image(page):
blocks = page.get_text('blocks')
return len(blocks) == 1 and blocks[0][6] == 1
def pdf_images(pdf, force=False): def pdf_images(pdf, force=False):
images_by_page = [page.get_images() for page in pdf] images_by_page = [(page.get_images(), is_single_image(page)) for page in pdf]
if all(len(images) == 1 for images in images_by_page): if all(len(images) == 1 and single for (images, single) in images_by_page):
return (pdf.extract_image(images[0][0]) for images in images_by_page) return (pdf.extract_image(images[0][0]) for (images, _) in images_by_page)
print("Checking PDF images the quick way failed, trying the slow way") print("Checking PDF images the quick way failed, trying the slow way")
def xref_or_image_generator(): def xref_or_image_generator():
xref_mode = not force xref_mode = not force
for (idx, page) in enumerate(pdf): for (idx, page) in enumerate(pdf):
page_images = page.get_image_info(xrefs=True) page_images = page.get_image_info(xrefs=True)
if len(page_images) == 1 and page_images[0]['xref'] != 0: if len(page_images) == 1 and page_images[0]['xref'] != 0 and is_single_image(page):
xref = page_images[0]['xref'] xref = page_images[0]['xref']
if xref_mode: if xref_mode:
yield xref yield xref