主函数可以类似这样:
for i in range(4):
main(i+1)
完整代码:
# -*- coding: utf-8 -*-
import requests
import re
import json
from requests.exceptions import RequestException
from multiprocessing import Pool
def get_one_page(url):
try:
response = requests.get(url)
if response.status_code == 200:
return response.content.decode("utf-8")
return None
except RequestException:
return None
def parse_one_page(html):
pattern = re.compile(\'<div>.*?lecturer-info.*?<span>(.*?)</span>.*?shizhan-intro-box.*?title=".*?">\'
\'(.*?)</p>.*?class="grade">(.*?)</span>.*?imv2-set-sns.*?</i>\'
\'(.*?)</span>.*?class="big-text">(.*?)</p>.*?shizan-desc.*?>\'
\'(.*?)</p>.*?</div>\',re.S)
items = re.findall(pattern,html)
for item in items:
yield {
\'teacher\': item[0],
\'title\': item[1],
\'grade\': item[2],
\'people\':item[3],
\'score\': item[4],
\'describe\': item[5]
}
def write_to_file(content):
with open(\'imoocAll.txt\',\'a\',encoding=\'utf-8\') as f:
f.write(json.dumps(content,ensure_ascii=False)+\'\n\')
f.close()
def main(page):
url = \'http://coding.imooc.com/?page=\'+str(page)
html = get_one_page(url)
# parse_one_page(html)
# print(html)
for item in parse_one_page(html):
print(item)
write_to_file(item)
if __name__ == \'__main__\':
pool = Pool()
pool.map(main,[i+1 for i in range(4)])
# for i in range(4):
#
main(i+1)
到这里,我们就能够把慕课网上面的全部实战课程的信息爬取下来,拿到这些数据,你就可以做自己喜爱的分析了
