python爬虫和数据可视化论文_Python爬虫实战数据可视化分析
#-*-coding:utf-8-*-importjsonimporttimeimportmultiprocessingimportrequestsfromlxmlimportetreeclassHandelLaGou(object):def__init__(self):self.lagou_session=requests.session()self.header={'...
#-*-coding:utf-8-*-
import json
import time
import multiprocessing
import requests
from lxml import etree
class HandelLaGou(object):
def __init__(self):
self.lagou_session = requests.session()
self.header = {
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/525.19 (KHTML, like Gecko) Chrome/0.4.154.18 Safari/525.19'
}
self.city_list = ""
def handle_city(self):
city_url = "https://www.lagou.com/jobs/allCity.html"
city_result = self.handle_request(method="GET", url=city_url)
list = city_result.xpath('//ul[contains(@class, "city_list")]/li/a/text()')
self.city_list = [x for x in list]
self.lagou_session.cookies.clear()
def handle_city_job(self, city):
first_request_url = "https://www.lagou.com/jobs/list_python?&px=default&city=%s"%city
first_response = self.handle_request(method="GET",url=first_request_url)
try:
total_page = first_response.xpath('//span[contains(@class, "span totalNum")]/text()')
print(total_page)
except:
return
else:
for i in range(1, int(total_page[0])+1):
data = {
"pn":i,
"kd":"python"
}
print(i)
page_url = "https://www.lagou.com/jobs/positionAjax.json?px=default&city=%s&needAddtionalResult=false"%city
referer_url = "https://www.lagou.com/jobs/list_python?&px=default&city=%s"%city
self.header['Referer'] = referer_url.encode('utf-8')
response = self.handle_request(method="POST", url=page_url, data=data, info=city)
lagou_data = json.loads(response)
job_list = lagou_data['content']['positionResult']['result']
for job in job_list:
print(job)
def handle_request(self, method, url , data=None, info=None):
while True:
if method == "GET":
response = self.lagou_session.get(url=url, headers=self.header)
item = etree.HTML(response.text)
elif method == "POST":
response = self.lagou_session.post(url=url, headers=self.header, data=data)
item = response.text
if '频繁' in response.text:
self.lagou_session.cookies.clear()
first_request_url = "https://www.lagou.com/jobs/list_python?&px=default&city=%s" %info
self.handle_request(method="GET", url=first_request_url)
time.sleep(15)
continue
return item
if __name__ == '__main__':
lagou = HandelLaGou()
lagou.handle_city()
pool = multiprocessing.Pool(2)
for city in lagou.city_list:
pool.apply_async(lagou.handle_city_job, args=(city,))
pool.close()
pool.join()
魔乐社区(Modelers.cn) 是一个中立、公益的人工智能社区,提供人工智能工具、模型、数据的托管、展示与应用协同服务,为人工智能开发及爱好者搭建开放的学习交流平台。社区通过理事会方式运作,由全产业链共同建设、共同运营、共同享有,推动国产AI生态繁荣发展。
更多推荐


所有评论(0)