用正则表达式+Requests爬取猫眼电影Top100

import json

import requests
import requests.exceptions
import re
#返回单页的信息
def get_single_page(url):
    response = requests.get(url)
    try:
        if(response.status_code ==200):
            return response.text
        return None
    except requests.exceptions.HTTPError:
        return None
#解析页面,用正则表达式获取想要的信息,这里注意的是,千万别用开发者模式查看网页的源码,源码可能和response.text不同
def  parseHtml(html):
    pattern= re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?data-act.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(\d+)</i>',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 writeIntoFile(item):
    with open('result.txt','a') as f:
        f.write(json.dumps(item)+'\n')
        f.close()
def main(url):
    html = get_single_page(url)
    for item in parseHtml(html):
        writeIntoFile(item)
        print(item)
for i in range(10):
    url = 'http://maoyan.com/board/4?offset='+str(i*10)
    main(url)