Python3抓取猫眼电影排行

程序运行结果如下图示：

代码如下：

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

def get_one_page(url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
    }
    try:
        response=requests.get(url,headers=headers)
        if response.status_code==200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):
    pattern=re.compile(
        '<dd>.*?board-index.*?>(.*?)</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_json(content):
    with open('result.txt','a',encoding='utf-8') as f:
        f.write(json.dumps(content,ensure_ascii=False)+'\n')

def main(offset):
    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_json(item)


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

出自  静觅 » [Python3网络爬虫开发实战] 3.4-抓取猫眼电影排行