Python爬虫【三】利用requests和正则抓取猫眼电影网上排名前100的电影

#利用requests和正则抓取猫眼电影网上排名前100的电影
import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool

def get_one_page(url):
    try:
        #需要重置requests的headers,否则猫眼电影拒绝访问。
        headers = {
            "user-agent": 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36'}
        response = requests.get(url,headers=headers)
    #加一个判断，判断请求URL是否成功
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):
    #解析网页的html代码
    pattern = re.compile('<dd>.*?board-index-1.*?>(d+)</i>.*?src="(.*?)".*?name"><a'
                         '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>',re.S)

    items = re.findall(pattern,html)
    #print(items)
    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') as f:
        f.write(json.dumps(content)+'
')
        f.close()

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_file(item)
    # print(html)



if __name__ == '__main__':
#设置多进程抓取
    pool = Pool()
    pool.map(main,[i*10 for i in range(10)])