入门学习python爬虫（一）爬取新华三的招聘信息

1. 导包

导入http工具类和lxml解析器

import requests
from lxml import html

2. 获取每个岗位的信息

#查询49页数据
for i in range(1,49):
	#网站url
    url="https://h3c.zhiye.com/search/?PageIndex={}".format(i)
    te=requests.get(url).text
    soup=html.fromstring(te)
    #通过html标签定位到数据
    tr=soup.xpath("//table[@class='listtable']/tr/td/a/text()")
    #文章详情url
    href = soup.xpath("//table[@class='listtable']/tr/td/a/@href")
    s=soup.xpath("//table[@class='listtable']/tr/td[2]")
    r=soup.xpath("//table[@class='listtable']/tr/td[3]")
    g=soup.xpath("//table[@class='listtable']/tr/td[4]/text()")
    for t in range(len(tr)):
    	#获取岗位信息
        print(tr[t].replace("\n","").replace(" ",""))
        print(s[t].text)
        print(r[t].text.replace("\n","").replace(" ",""))
        print(g[t].replace("\n", "").replace(" ", ""))

3. 获取每个岗位的详情信息

通过上面函数获取到详情url，解析数据

def get_utls(url1):
    url1 = 'https://h3c.zhiye.com' + url1
    print(url1)
    te1=requests.get(url1).text
    soup1=html.fromstring(te1)
    a=soup1.xpath("//li[@class='nvalue']/text()")
    print(a[0].replace("\n","").replace(" ",""))
    print(a[1].replace("\n", "").replace(" ", ""))
    print(a[2].replace("\n", "").replace(" ", ""))
    print(a[3].replace("\n", "").replace(" ", ""))
    print(a[4].replace("\n", "").replace(" ", ""))
    print(a[5].replace("\n", "").replace(" ", "").replace("\xa0", ""))

4. 完整代码

import requests
from lxml import html
#xpath
def get_utls(url1):
    url1 = 'https://h3c.zhiye.com' + url1
    print(url1)
    te1=requests.get(url1).text
    soup1=html.fromstring(te1)
    a=soup1.xpath("//li[@class='nvalue']/text()")
    print(a[0].replace("\n","").replace(" ",""))
    print(a[1].replace("\n", "").replace(" ", ""))
    print(a[2].replace("\n", "").replace(" ", ""))
    print(a[3].replace("\n", "").replace(" ", ""))
    print(a[4].replace("\n", "").replace(" ", ""))
    print(a[5].replace("\n", "").replace(" ", "").replace("\xa0", ""))
for i in range(1,49):
    url="https://h3c.zhiye.com/search/?PageIndex={}".format(i)
    te=requests.get(url).text
    soup=html.fromstring(te)
    tr=soup.xpath("//table[@class='listtable']/tr/td/a/text()")
    href = soup.xpath("//table[@class='listtable']/tr/td/a/@href")
    s=soup.xpath("//table[@class='listtable']/tr/td[2]")
    r=soup.xpath("//table[@class='listtable']/tr/td[3]")
    g=soup.xpath("//table[@class='listtable']/tr/td[4]/text()")
    for t in range(len(tr)):
        print(tr[t].replace("\n","").replace(" ",""))
        print(s[t].text)
        print(r[t].text.replace("\n","").replace(" ",""))
        print(g[t].replace("\n", "").replace(" ", ""))
        get_utls(href[t])