-
爬取前程无忧职位信息
此次我们用简单的爬虫来展示如何把爬到提取出的信息保存的excel文件中.(ps:首先你要安装好模块openpyxl否则就点击右上角离开,百度搜素安装.)
选前程无忧的网页作为案例是因为主编最近在看看工作的消息,想想就顺手写了一个为方便寻找满足自己要求的工作.为简化我们爬虫的需求,我们已经在前程无忧上的页面选择自己对应的职位需求和职位地区.我选的是杭州+互联网/电子商务对应的url地址是前程无忧
import requests
from lxml import etree
from openpyxl import Workbook
class Job():
def __init__(self):
self.url = 'https://search.51job.com/list/080200,000000,0000,32,9,99,%2B,2,{页数}.html'
self.header = {
"User-Agent": "User-Agent:Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
"Connection": "keep - alive",
}
self.wb = Workbook()# class实例化
self.ws = self.wb.active# 激活工具表
self.ws.append(['job', 'company', 'locate', 'salary', 'time'])# 添加对应的表头
# 构造访问的url地址
def geturl(self):
url = [self.url.format(页数 =i) for i in range(1,9)]
# 分析页面url获取的规则
return url
# 发出页面相应请求
def parse_url(self,url):
response =requests.get(url,headers =self.header,timeout = 5)
return response.content.decode('gbk','ignore')
# 提取页面的对应的信息
def get_list(self,html_str):
html = etree.HTML(html_str)
connect_list = []
lists = html.xpath("//div[@class ='el']")
for list in lists:
item = {}
item['job'] = ''.join(list.xpath("./p/span/a/@title"))
item['company'] = ''.join(list.xpath("./span[@class = 't2']/a/@title"))
item['locate'] = ''.join(list.xpath("./span[@class = 't3']/text()"))
item['salary'] = ''.join(list.xpath("./span[@class = 't4']/text()"))
item['time'] = ''.join(list.xpath("./span[@class = 't5']/text()"))
# "".join(...)将列表转换为字符串的数据形式,方便保存到excel表格中
connect_list.append(item)
return connect_list
# 保存提取的相关信息(.xlsx的形式保存进去)
def save_list(self, connects):
for connect in connects:
self.ws.append([connect['job'], connect['company'], connect['locate'], connect['salary'], connect['time']])
print('保存成功页招聘信息')
# 启动爬虫
def run(self):
url_list = self.geturl()
for url in url_list:
html_url =self.parse_url(url)
connects = self.get_list(html_url)
self.save_list(connects[4:])
# 提取到的信息中每页前四个为空白信息
self.wb.save('job.xlsx')
# 保存excel设置在这里是为让信息全部保存,
# 如果放在save_list中会最好每次只保存一个页面上的信息不会以追加的形式写入excel
if __name__=='__main__':
spider = Job()
spider.run()
注意:欢迎大家指出意见,相互学习哦~