#!/usr/bin/python
#!coding=utf-8
import json
import requests
import re
import time
def get_one_page(url):
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36'}
response = requests.get(url,headers=headers)
if response.status_code == 200:
return response.text
return None
def parse_one_page(html):
pattern = re.compile(
'<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?<a.*?title="(.*?)".*?</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">'+
'(.*?)</i>.*?fraction.*?>(\d).*?</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','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):
write_to_file(item)
if __name__ == "__main__":
for i in range(10):
main(i*10)
time.sleep(1)
Python爬虫
最新推荐文章于 2024-07-27 11:46:57 发布