我正在尝试使用 Camelot 从 pdf 中提取表格数据。使用参数“table_regions”时,我得到并错误“解包的值太多(预期为 4)”
tables = camelot.read_pdf('BOA1.pdf',flavor="stream",pages="3",table_regions=['1,1,1,1'])
导致:
ValueError Traceback (most recent call last)
<ipython-input-154-681440b4cbbd> in <module>()
----> 1 tables = camelot.read_pdf('BOA1.pdf',flavor="stream",pages="3-20",table_regions=['1,1,1,1'])
~\Anaconda3\lib\site-packages\camelot\io.py in read_pdf(filepath, pages, password, flavor, suppress_stdout, layout_kwargs, **kwargs)
104 kwargs = remove_extra(kwargs, flavor=flavor)
105 tables = p.parse(flavor=flavor, suppress_stdout=suppress_stdout,
--> 106 layout_kwargs=layout_kwargs, **kwargs)
107 return tables
~\Anaconda3\lib\site-packages\camelot\handlers.py in parse(self, flavor, suppress_stdout, layout_kwargs, **kwargs)
160 for p in pages:
161 t = parser.extract_tables(p, suppress_stdout=suppress_stdout,
--> 162 layout_kwargs=layout_kwargs)
163 tables.extend(t)
164 return TableList(tables)
~\Anaconda3\lib\site-packages\camelot\parsers\stream.py in extract_tables(self, filename, suppress_stdout, layout_kwargs)
417 return []
418
--> 419 self._generate_table_bbox()
420
421 _tables = []
~\Anaconda3\lib\site-packages\camelot\parsers\stream.py in _generate_table_bbox(self)
287 hor_text = []
288 for region in self.table_regions:
--> 289 x1, y1, x2, y2 = region
290 region_text = text_in_bbox((x1, y2, x2, y1), self.horizontal_text)
291 hor_text.extend(region_text)
ValueError: too many values to unpack (expected 4)