使用BeautifuSoup4的爬虫

我们以腾讯社招页面来做演示：http://hr.tencent.com/position.php?&start=10#a

使用BeautifuSoup4解析器，将招聘网页上的职位名称、职位类别、招聘人数、工作地点、发布时间，以及每个职位详情的点击链接存储出来。

from bs4 import BeautifulSoup
import urllib.request
import json    # 使用了json格式存储

def tencent():
    url = 'http://hr.tencent.com/'
    request = urllib.request.Request(url + 'position.php?&start=10#a')
    response =urllib.request.urlopen(request)
    resHtml = response.read()

    output =open('tencent.json','wb+')

    html = BeautifulSoup(resHtml,'lxml')

# 创建CSS选择器
    result = html.select('tr[class="even"]')
    result2 = html.select('tr[class="odd"]')
    result += result2
    print(result)
    items = []
    for site in result:
        item = {}

        name = site.select('td a')[0].get_text()
        detailLink = site.select('td a')[0].attrs['href']
        catalog = site.select('td')[1].get_text()
        recruitNumber = site.select('td')[2].get_text()
        workLocation = site.select('td')[3].get_text()
        publishTime = site.select('td')[4].get_text()

        item['name'] = name
        item['detailLink'] = url + detailLink
        item['catalog'] = catalog
        item['recruitNumber'] = recruitNumber
        item['publishTime'] = publishTime
        item['workLocation'] = workLocation

        items.append(item)

    # 禁用ascii编码，按utf-8编码
    line = json.dumps(items,ensure_ascii=False)

    output.write(line.encode())
    output.close()

if __name__ == "__main__":
   tencent()

爬取结果tencent.json

[
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40821&keywords=&tid=0&lid=0", 
"workLocation": "北京", 
"catalog": "职能类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", "name": 
"S2-MIG风险管理经理(北京）"
}, 
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40825&keywords=&tid=0&lid=0", 
"workLocation": "深圳", 
"catalog": "市场类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", 
"name": "19116-互联网+医疗行业经理（深圳）"
}, 
{"detailLink": "http://hr.tencent.com/position_detail.php?id=40815&keywords=&tid=0&lid=0", 
"workLocation": "深圳", 
"catalog": "技术类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", 
"name": "24012-H5游戏开发工程师（深圳）"
}, 
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40818&keywords=&tid=0&lid=0", 
"workLocation": "北京", 
"catalog": "设计类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", 
"name": "23674-视觉设计（北京）"
}, 
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40820&keywords=&tid=0&lid=0", 
"workLocation": "深圳", 
"catalog": "设计类", 
"publishTime": "2018-05-24", 
"recruitNumber": "2", 
"name": "24491-高级多媒体设计师（深圳）"
}, 
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40824&keywords=&tid=0&lid=0", 
"workLocation": "深圳", 
"catalog": "技术类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", 
"name": "26564-后台开发工程师(深圳）"
}, 
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40828&keywords=&tid=0&lid=0", 
"workLocation": "深圳", 
"catalog": "市场类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", 
"name": "MIG15-腾讯叮当高级销售经理"
}, 
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40817&keywords=&tid=0&lid=0", 
"workLocation": "深圳", 
"catalog": "产品/项目类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", 
"name": "26564-项目经理（深圳）"
}, 
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40819&keywords=&tid=0&lid=0", 
"workLocation": "深圳", 
"catalog": "产品/项目类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", 
"name": "24491-游戏英文文案翻译（深圳）"
}, 
{
"detailLink": "http://hr.tencent.com/position_detail.php?id=40822&keywords=&tid=0&lid=0", 
"workLocation": "深圳", 
"catalog": "产品/项目类", 
"publishTime": "2018-05-24", 
"recruitNumber": "1", 
"name": "SD3-海外PM（日语方向）"
}
]

使用BeautifuSoup4的爬虫

猜你喜欢