Python爬取招聘网站招聘信息

仅供个人学习笔记使用。

from lxml import etree

parser = etree.HTMLParser(encoding='utf-8')
html = etree.parse('招聘网站.html',parser=parser)
#1、获取所有li标签
# //li
# xpath函数返回的是一个列表
trs = html.xpath('//li')
for li in trs:
    print(etree.tostring(li,encoding='utf-8').decode('utf-8'))

# 2、获取第2个li标签
li = html.xpath('//li[1]')[0]
print(etree.tostring(li,encoding='utf-8').decode('utf-8'))

# #3、获取所有class等于con_list_item的li标签
trs = html.xpath("//li[@class='con_list_item first_row default_list']")
for li in trs:
    print(etree.tostring(li,encoding='utf-8').decode('utf-8'))

# #4、获取所有a标签的href属性
aList = html.xpath('//a[@href]')
for a in aList:
    print(etree.tostring(a, encoding='utf-8').decode('utf-8'))

# #5、获取所有的职位信息（纯文本）
trs = html.xpath('//li[position()>0]')
positions =[]
for li in trs:
    # 在某个标签下，再执行xpath函数，获取这个标签下的子孙元素，那么应该在//之前加一个点，代表当前元素下获取
    url = li.xpath('.//a/@href')[0]

    position = li.xpath(".//h3/text()")[0]
    salary = li.xpath(".//span[@class='money']/text()")[0]
    job_exper = li.xpath(".//div[@class='li_b_l']/text()")[2]
    zhaopin_date = li.xpath(".//span[@class='format-time']/text()")[0]
    company = li.xpath(".//div/a[@data-lg-tj-id='8F00']/text()")[0]
    company_size = li.xpath(".//div[@class='industry']/text()")[0]
    introduce = li.xpath(".//div[@class='li_b_r']/text()")[0]

    position = {
        '网址':url.strip(),
        '公司地址':position.strip(),
        '薪资':salary.strip(),
        '工作经验':job_exper.strip(),
        '招聘日期':zhaopin_date.strip(),
        '公司名称':company.strip(),
        '公司规模':company_size.strip(),
        '公司介绍':introduce.strip()
    }
    positions.append(position)
print(positions)