|
|
马上注册,结交更多好友,享用更多功能^_^
您需要 登录 才可以下载或查看,没有账号?立即注册
x
import requests
from multiprocessing import Pool
from requests.exceptions import RequestException
import re
import json
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.*?>(\d+)</i>.*?board-img.*?src"(.*?)".*?>name"><a.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>.*?integer">(.*?)</i>.*?fraction">(.*?)</i></p>', re.S)
items = re.findall(pattern, html)
parse_one_page(html)
for item in items:
yield {
'index' : item[0],
'img': item[1],
'title': item[2],
'actor': item[3].strip()[3:0],
'time': item[4].strip()[5:0],
'score': item[5] + item[6],
}
def write_to_file(content):
with open('result.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)
if __name__ == '__main':
pool = Pool()
pool.map(main, [i*10 for i in range(10) ]) |
|