def get_page(url):
  response = requests.get(url)
  if response.status_code == 200:
    return response.text
  return None

def parse_page(html):
  pattern = re.compile('<li.*">(.*"htmlcode">

def write_to_file(content):
  with open('result.txt', 'a', encoding='utf-8')as f:
    f.write(json.dumps(content, ensure_ascii=False) + '\n')#将字典格式转换为字符串加以保存，并设置中文格式
    f.close()


五，调用函数


def main():
  url = 'https://list.iqiyi.com/www/1/-------------8-1-1-iqiyi--.html'
  html = get_page(url)
  for item in parse_page(html):
    print(item)
    write_to_file(item)


六，运行结果


七，完整代码


import json
import requests
import re


# 抓取html文件
# 解析html文件
# 存储文件


def get_page(url):
  response = requests.get(url)
  if response.status_code == 200:
    return response.text
  return None


def parse_page(html):
  pattern = re.compile('<li.*">(.*?)<.*?title.*?>(.*?)<.*?title.*?>(.*?)<', re.S)
  items = re.findall(pattern, html)
  for item in items:
    yield {
      'score': item[0],
      'name': item[1],
      'actor': item[2].strip()[3:]
    }


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 = 'https://list.iqiyi.com/www/1/-------------8-1-1-iqiyi--.html'
  html = get_page(url)
  for item in parse_page(html):
    print(item)
    write_to_file(item)
if __name__ == '__main__':
  main()


以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。