PhantomJSで収集したデータのcsvへの格納
以前質問をさせて頂いたPhantomJSをGoogle Colab上で用いて、データスクレイピングの練習をしています。
が、データをcsvファイル内にうまく格納できず下の様なエラーが出てしまいます...。
どの様に対応すれば良いでしょうか...?
コード
!pip install selenium
# PhantomJS をダウンロード
!wget https://bitbucket.org/ariya/phantomjs/downloads/phantomjs-2.1.1-linux-x86_64.tar.bz2
!tar xf phantomjs-2.1.1-linux-x86_64.tar.bz2
#https://review-of-my-life.blogspot.com/2017/10/python-web-scraping-data-collection-analysis.htmlの練習
#trendAnalytics.py
from selenium import webdriver
from pandas import *
import time
#Access to page
# PATH を指定した上で WebDriver を用意
browser = webdriver.PhantomJS(executable_path="/content/phantomjs-2.1.1-linux-x86_64/bin/phantomjs") #PhantomJSのサポートは終わっているらしい...?Headless Chromeを使うべきなのか...?
# DO NOT FORGET to set path
url = "http://b.hatena.ne.jp/search/text?safe=on&q=Python&users=50"
browser.get(url)
!touch trend.csv
df = pandas.read_csv('trend.csv',index_cols=0) #下のエラーの要因
エラー
/usr/local/lib/python3.6/dist-packages/selenium/webdriver/phantomjs/webdriver.py:49: UserWarning: Selenium support for PhantomJS has been deprecated, please use headless versions of Chrome or Firefox instead
warnings.warn('Selenium support for PhantomJS has been deprecated, please use headless '
---------------------------------------------------------------------------
EmptyDataError Traceback (most recent call last)
<ipython-input-4-f17876ff531c> in <module>()
11 browser.get(url)
12 get_ipython().system('touch trend.csv')
---> 13 df = pandas.read_csv('trend.csv') #下のエラーの要因
14
15 #Insert title,date,bookmarks into CSV file
/usr/local/lib/python3.6/dist-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)
707 skip_blank_lines=skip_blank_lines)
708
--> 709 return _read(filepath_or_buffer, kwds)
710
711 parser_f.__name__ = name
/usr/local/lib/python3.6/dist-packages/pandas/io/parsers.py in _read(filepath_or_buffer, kwds)
447
448 # Create the parser.
--> 449 parser = TextFileReader(filepath_or_buffer, **kwds)
450
451 if chunksize or iterator:
/usr/local/lib/python3.6/dist-packages/pandas/io/parsers.py in __init__(self, f, engine, **kwds)
816 self.options['has_index_names'] = kwds['has_index_names']
817
--> 818 self._make_engine(self.engine)
819
820 def close(self):
/usr/local/lib/python3.6/dist-packages/pandas/io/parsers.py in _make_engine(self, engine)
1047 def _make_engine(self, engine='c'):
1048 if engine == 'c':
-> 1049 self._engine = CParserWrapper(self.f, **self.options)
1050 else:
1051 if engine == 'python':
/usr/local/lib/python3.6/dist-packages/pandas/io/parsers.py in __init__(self, src, **kwds)
1693 kwds['allow_leading_cols'] = self.index_col is not False
1694
-> 1695 self._reader = parsers.TextReader(src, **kwds)
1696
1697 # XXX
pandas/_libs/parsers.pyx in pandas._libs.parsers.TextReader.__cinit__()
EmptyDataError: No columns to parse from file