爬虫——爬取猫眼电影网

import json
from multiprocessing import Pool
import requests
from requests.exceptions import RequestException
import re

def get_one_page(url):
try:
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)
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.*?>(\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('E:\\doc\\bawei\\pachong\\maoyan_movie_result.txt', 'a', encoding='utf-8') as f: #路径
f.write(json.dumps(content, ensure_ascii=False) + '\n')
f.close()

def main(offset):
url = 'http://maoyan.com/board/4?offset='+str(offset)
url='http://www.baidu.com'
html = get_one_page(url)
# print(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()  # 建立进程池
pool.map(main, (i * 10 for i in range(10)))  # 映射到主函数中进行循环