python requests 正则爬虫

Posted 2021-02-09 石

代码：

import requests
from multiprocessing import Pool
from requests.exceptions import RequestException
import re
import  json
def get_one_page(url):
    try:
        if url==‘‘:
            return None
        response=requests.get(url)
        if response.status_code==200:
            return response.text
        return None
    except RequestException:
        return None

def parse_one_page(html):
    if html==‘‘:
        return None
    pattern=re.compile(‘<dd>.*?board-index.*?>(d+)</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_file(content):
    with open(‘result.txt‘,‘a‘,encoding=‘utf-8‘) as f:#a往后追加
        f.write(json.dumps(content,ensure_ascii=False)+‘
‘)
        f.close()

def main(offset):
    url=‘http://maoyan.com/board/4?offset=‘+str(offset)
    html=get_one_page(url)  # 得到html
    for item in  parse_one_page(html):
       print(item)
       write_to_file(item)

if __name__==‘__main__‘:
    # for i in range(10):
    #     main(i*10)
    pool=Pool() #多线程
    pool.map(main,[i*10 for i in range(10)])