猫眼电影Top100爬取

import requests
import re
import json
import time
from requests.exceptions import RequestException
"""猫眼电影Top100爬取"""


def get_one_page(url):
   """请求页面，若成功则返回页面的内容"""
   try:
      # 设置请求头，
      headers = {
         'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_3)\
         AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.162 Safari/537.36'
      }
      response = requests.get(url, headers=headers)
      # 若请求成功，返回响应的内容
      if response.status_code == 200:
         # print(response.text)
         return response.text
      return None
   # 出现异常返回None
   except RequestException:
      return None


def parse_one_page(html):
   """解析页面，提取需要的信息"""
   pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name.*?a.*?>(.*?)</a>.*?'
                        'star.*?>(.*?)</p>.*?releasetime.*?>(.*?)</p>.*?integer.*?>'
                        '(.*?)</i>.*?fraction.*?>(\d*)</i>.*?</dd>', re.S)
   # 找出所有符合正则式的信息
   items = re.findall(pattern, html)
   for item in items:
      # print(item)
      # yield用于生成一个可迭代器
      yield {
         'index': item[0],
         'image': item[1],
         'name': item[2].strip(),
         'actor': item[3].strip()[3:] if len(item[3]) > 3 else '',
         'time': item[4].strip()[5:] if len(item[4]) > 5 else '',
         'score': item[5].strip()+item[6].strip(),
      }


def write_to_file(content):
   """写入本地文件"""
   with open('result.txt', 'a', encoding='utf-8') as f:
      f.write(json.dumps(content, ensure_ascii=False)+'\n')


def main(offset):
   """主函数，用于调用其他函数"""
   url = 'http://maoyan.com/board/4?offset=' + str(offset)
   html = get_one_page(url)
   for item in parse_one_page(html):
      # print(item)
      write_to_file(item)


if __name__ == '__main__':
   for i in range(10):
      main(offset=i*10)
      time.sleep(1)