import re
import requests
from requests.exceptions import RequestException
import json


def get_one_page(url):
try:

response = requests.get(url)
if response.status_code == 200:
return response.content
return None
    except RequestException:
return None


def parse_page_html(html):

pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'+ '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'+ '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)


items = re.findall(pattern, html)
for item in items:
yield {
'index':item[0],
'image':item[1],
'title':item[2],
'actor':item[3].strip()[3:],
'time':item[4].strip()[5:],
'score':item[5]+item[6]

}

def write_to_file(content):
with open('result.txt','a',encoding='utf-8') as f:

f.write(json.dumps(content,ensure_ascii=False)+'\n')

f.close()

def main():

url = 'http://maoyan.com/board/4?'
    html = get_one_page(url)
for item in parse_page_html(html):

write_to_file(item)


if __name__ == '__main__':

main()

如果没有以上红色代码，会出现TypeError: cannot use a string pattern on a bytes-like object，只需要加上html = html.decode('utf-8')即可