tabula-py: Extract table from PDF into Python DataFrame
Aki Ariga
937

I am getting error when I use read_pdf(‘http://www.wrldc.in/9_reportNew/dailydata_01082017.pdf’).

---------------------------------------------------------------------------
ParserError Traceback (most recent call last)
<ipython-input-10-cc2636d32540> in <module>()
----> 1 data = read_pdf('http://www.wrldc.in/9_reportNew/dailydata_01082017.pdf')

/Users/sourabhjain/anaconda3/lib/python3.6/site-packages/tabula/wrapper.py in read_pdf(input_path, output_format, encoding, java_options, pandas_options, multiple_tables, **kwargs)
95 pandas_options['encoding'] = pandas_options.get('encoding', encoding)
96
---> 97 return pd.read_csv(io.BytesIO(output), **pandas_options)
98
99

/Users/sourabhjain/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in parser_f(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, skip_footer, doublequote, delim_whitespace, as_recarray, compact_ints, use_unsigned, low_memory, buffer_lines, memory_map, float_precision)
653 skip_blank_lines=skip_blank_lines)
654
--> 655 return _read(filepath_or_buffer, kwds)
656
657 parser_f.__name__ = name

/Users/sourabhjain/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
409
410 try:
--> 411 data = parser.read(nrows)
412 finally:
413 parser.close()

/Users/sourabhjain/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in read(self, nrows)
980 raise ValueError('skipfooter not supported for iteration')
981
--> 982 ret = self._engine.read(nrows)
983
984 if self.options.get('as_recarray'):

/Users/sourabhjain/anaconda3/lib/python3.6/site-packages/pandas/io/parsers.py in read(self, nrows)
1717 def read(self, nrows=None):
1718 try:
-> 1719 data = self._reader.read(nrows)
1720 except StopIteration:
1721 if self._first_chunk:

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.read (pandas/_libs/parsers.c:10862)()

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._read_low_memory (pandas/_libs/parsers.c:11138)()

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._read_rows (pandas/_libs/parsers.c:11884)()

pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader._tokenize_rows (pandas/_libs/parsers.c:11755)()

pandas/_libs/parsers.pyx in pandas._libs.parsers.raise_parser_error (pandas/_libs/parsers.c:28765)()

ParserError: Error tokenizing data. C error: Expected 10 fields in line 18, saw 11

Kindly, help. I am using Mac- Sierra 10.12.4 and Jupyter Notebook. I have Java version 8 update 111.

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.