Requests加正则表达式抓取猫电影信息

#Author:donghuiya
#这是抓取猫眼电影前100页，分四步：
#1.得到网页源代码
#2.用正则表达式获得所需要的内容
#3.写入文件中
#4.用多进程更快
import requests
from requests.exceptions import RequestException
import re
import json
from multiprocessing import Pool
def get_one_page(url):
try:
response=requests.get(url)
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>.*?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],
'title':item[1],
'actor':item[2].strip()[3:],
'time':item[3].strip()[5:],
'score':item[4]+item[5]
}
def write_to_file(content):
with open('result1.txt','a',encoding="utf-8") as f:
f.write(json.dumps(content,ensure_ascii=False)+'\n')
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)
if __name__=='__main__':
pool=Pool()
pool.map(main,[i*10 for i in range(10)])