Python爬取拉勾网贾科斯动态加载网页——代码可直接运行

# 代码可直接运行
import requests
import json,time,math
headers={
    'Accept': 'application/json, text/javascript, */*; q=0.01',
    'Accept-Encoding': 'gzip, deflate, br',
    'Accept-Language': 'zh-CN,zh;q=0.9',
    'Connection': 'keep-alive',
    'Content-Length': '22',
    'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'Cookie': 'WEBTJ-ID=20180611163422-163edfb57cd121-0bb2a8f27f81c7-3a61430c-1382400-163edfb57cf10a; _ga=GA1.2.1531784824.1528706063; _gid=GA1.2.2041642098.1528706063; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1528706063; user_trace_token=20180611163423-3e924b1b-6d52-11e8-9446-5254005c3644; LGSID=20180611163423-3e92506f-6d52-11e8-9446-5254005c3644; PRE_UTM=m_cf_cpc_baidu_pc; PRE_HOST=www.baidu.com; PRE_SITE=https%3A%2F%2Fwww.baidu.com%2Fbaidu.php%3Fsc.0f0000aPftK-mFJ6dmSXMsql8ZwbuxSPbcy2vJ_PiH0fF3UDhEy4UsZhM2Uj1XbZkGsOMVGu-wtPW1ORpV7f_WOq_sSzEW6tvi7jy8EoKIiQUVjNRIMhGF4BChaLbTpB9d3Dbtt6ALf8H_TczdmliDkCdmw8Y1BaGHziVDFrD1pFpDUZF0.DY_NR2Ar5Od663rj6tJQrGvKD7ZZKNfYYmcgpIQC8xxKfYt_U_DY2yP5Qjo4mTT5QX1BsT8rZoG4XL6mEukmryZZjzsdwdTJplePXO-8zNqrw5Q9tSMj_qTr1x9tqvZul3xg1sSxW9qx-9LdJN9h9mzUOZxyC0.U1Yk0ZDqs2v4VnL30ZKGm1Yk0Zfqs2v4VnL30A-V5HcsP0KM5yF-TZnk0ZNG5yF9pywd0ZKGujYkPsKWpyfqn1Rz0AdY5HDsnHIxnH0krNtknjc1g1DsPjwxn1msnfKopHYs0ZFY5HmL0ANGujYzPWmsn7tzPWRzP7tkPjRzg1cknHcLg1csrj61g1cvPHT40AFG5HcsP0KVm1YLnWbvnWTsPjNxnH0snNtkg1Dsn-ts0Z7spyfqn0Kkmv-b5H00ThIYmyTqn0K9mWYsg100ugFM5H00TZ0qn10dPjmznHcdP6K8IM0qna3snj0snj0sn0KVIZ0qn0KbuAqs5H00ThCqn0KbugmqTAn0uMfqn0KspjYs0Aq15H00mMTqnH00UMfqn0K1XWY0IZN15HT3PjD3rjbsPHfzrHDkPHTYnjn0ThNkIjYkPHc3P10vnjRLPjbL0ZPGujd9mvRvujuWrH0snjKWnARv0AP1UHYLrjmzwbFawHc3fYNDfYn30A7W5HD0TA3qn0KkUgfqn0KkUgnqn0KlIjYs0AdWgvuzUvYqn7tsg1KxnH0YP-ts0Aw9UMNBuNqsUA78pyw15HKxn7tsg1nkrjm4ndts0ZK9I7qhUA7M5H00uAPGujYzPW6Yn1RYPHm0ugwGujYVnfK9TLKWm1Ys0ZNspy4Wm1Ys0Z7VuWYs0AuWIgfqn0KhXh6qn0Khmgfqn0KlTAkdT1Ys0A7buhk9u1Yk0Akhm1Ys0APzm1YkPWm3n0%26ck%3D7824.1.89.240.562.229.556.191%26shh%3Dwww.baidu.com%26us%3D1.0.1.0.0.0.0%26ie%3DUTF-8%26f%3D8%26tn%3Dbaidu%26wd%3D%25E6%258B%2589%25E5%258B%25BE%25E7%25BD%2591%26oq%3D%25E6%258B%2589%25E5%258B%25BE%25E7%25BD%2591%26rqlang%3Dcn%26bc%3D110101; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2Flp%2Fhtml%2Fcommon.html%3Futm_source%3Dm_cf_cpc_baidu_pc%26m_kw%3Dbaidu_cpc_chsh_e110f9_d2162e_%25E6%258B%2589%25E5%258B%25BE%25E7%25BD%2591; LGUID=20180611163423-3e92525d-6d52-11e8-9446-5254005c3644; _putrc=91712340FB9621C4123F89F2B170EADC; JSESSIONID=ABAAABAABEEAAJA9A9CF61DE3F6F9BC690A96FB80EEB47C; login=true; hasDeliver=0; unick=%E9%BD%90%E5%85%B5; showExpriedIndex=1; showExpriedCompanyHome=1; showExpriedMyPublish=1; gate_login_token=eb820804f112a66648f3bf3ad6cd1f279f53d2b53e00ec3ebf1c491043dc2354; TG-TRACK-CODE=index_navigation; index_location_city=%E5%85%A8%E5%9B%BD; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1528706323; LGRID=20180611163842-d8848d06-6d52-11e8-99cc-525400f775ce; SEARCH_ID=2215451d15e64669acd9af4e309ee209',
    'Host': 'www.lagou.com',
    'Origin':'https://www.lagou.com',
    'Referer':'https://www.lagou.com/jobs/list_web?labelWords=&fromSearch=true&suginput=',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.146 Safari/537.36',
    'X-Anit-Forge-Code': '0',
    'X-Anit-Forge-Token': 'None',
    'X-Requested-With': 'XMLHttpRequest'
}
def spider(url,params):
    try:
        req = requests.post(url=url, headers=headers, data=params)
        jd=json.loads(req.text)
        results=jd['content']['positionResult']['result']
        for result in results:
            print(result['companyFullName'])
            time.sleep(1)
    except:
        pass
if __name__=='__main__':
    for pn in range(1,4):
        url = 'https://www.lagou.com/jobs/positionAjax.json'
        params = {
            'first': 'true',
            'pn': pn,
            'kd': 'web'
        }
        spider(url,params)

猜你喜欢

转载自blog.csdn.net/weixin_42080280/article/details/80855101