janedoesrepo / pdfreader Goto Github PK

TypeError                                 Traceback (most recent call last)
<ipython-input-97-9595bf47c47f> in <module>
     29 
     30 example_file = data_dir / "test.pdf"
---> 31 page_layouts = extract_page_layouts(example_file)
     32 print("Number of pages: %d" % len(page_layouts))

<ipython-input-97-9595bf47c47f> in extract_page_layouts(file)
     23         layouts = []
     24         for page in PDFPage.create_pages(document):
---> 25             interpreter.process_page(page)
     26             layouts.append(device.get_result())
     27 

/mnt/hd1/marsella/law_unpacker/venv/lib/python3.6/site-packages/pdfminer/pdfinterp.py in process_page(self, page)
    893             ctm = (1, 0, 0, 1, -x0, -y0)
    894         self.device.begin_page(page, ctm)
--> 895         self.render_contents(page.resources, page.contents, ctm=ctm)
    896         self.device.end_page(page)
    897         return

/mnt/hd1/marsella/law_unpacker/venv/lib/python3.6/site-packages/pdfminer/pdfinterp.py in render_contents(self, resources, streams, ctm)
    906         self.init_resources(resources)
    907         self.init_state(ctm)
--> 908         self.execute(list_value(streams))
    909         return
    910 

/mnt/hd1/marsella/law_unpacker/venv/lib/python3.6/site-packages/pdfminer/pdfinterp.py in execute(self, streams)
    922             if isinstance(obj, PSKeyword):
    923                 name = keyword_name(obj)
--> 924                 method = 'do_%s' % name.replace('*', '_a').replace('"', '_w')\
    925                     .replace("'", '_q')
    926                 if hasattr(self, method):

TypeError: a bytes-like object is required, not 'str'