第53讲 爬虫

raimond

import urllib.request
import chardet

def main():
    i = 0

    with open("urls.txt", 'r') as f:
        urls = f.read().splitlines()

    for each_url in urls:
        response = urllib.request.urlopen(each_url)
        html = response.read()

        encode = chardet.detect(html)['encoding']
        if encode == 'GB2312':
            encode = 'GBK'

        i += 1
        filename = 'url_%d.txt'% i

        with open(filename, 'w', encoding = encode) as each_file:
            each_file.write(html.decode(encode, 'ignore'))

if __name__ == '__main__':
    main()

==================== RESTART: C:/Users/user/Desktop/df.py ====================
Traceback (most recent call last):
  File "C:/Users/user/Desktop/df.py", line 25, in <module>
    main()
  File "C:/Users/user/Desktop/df.py", line 22, in main
    each_file.write(html.decode(encode))
TypeError: decode() argument 1 must be str, not None
>>>
上面是什么原因报错？

waitforlove

TypeError: decode() argument 1 must be str, not None