selenium抓取动态网页数据

import requests from lxml import etree import time import re 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", "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36", "Referer":"/jobs/list_python?labelWords=&fromSearch=true&suginput=", "Origin":"", "Host":"", "Content-Type":"application/x-www-form-urlencoded; charset=UTF-8", "Cookie":"_ga=GA1.2.1602115737.1553064534; user_trace_token=20190320144853-39b1375a-4adc-11e9-a253-525400f775ce; LGUID=20190320144853-39b13f88-4adc-11e9-a253-525400f775ce; WEBTJ-ID=20190408120043-169fb1afd63488-06179b118ca307-7a1437-2073600-169fb1afd648ed; _gid=GA1.2.1826141825.1554696044; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%22169fb1bb2c41ea-04951e55adc96a-7a1437-2073600-169fb1bb2c58d0%22%2C%22%24device_id%22%3A%22169fb1bb2c41ea-04951e55adc96a-7a1437-2073600-169fb1bb2c58d0%22%7D; sajssdk_2015_cross_new_user=1; _putrc=4C5D2603888320CA; JSESSIONID=ABAAABAAADEAAFIB00F5DDE71D51610901CB9E0031812BA; login=true; unick=%E4%BC%8D%E6%99%93%E4%B8%BD; showExpriedIndex=1; showExpriedCompanyHome=1; showExpriedMyPublish=1; hasDeliver=49; gate_login_token=7b04a40da89145a1fbc90a3d719616d28c8b0a303344ac37; index_location_city=%E6%88%90%E9%83%BD; X_MIDDLE_TOKEN=1221e6b5040722dc86f5ceb557e11965; _gat=1; LGSID=20190408151935-a9976fbf-59ce-11e9-8cc8-5254005c3644; PRE_UTM=m_cf_cpc_baidu_pc; PRE_HOST=; PRE_SITE=https%3A%2F%%%3Fsc.Ks000001qLT2daZnZWIez3ktR_jhHue3tONZubxU9mivhxeuj-Fxrjg6NnVcKTp-GYJ_YRvrc9_yOJ4uV-IEpfnPazPz7ctjve1qlDokCDfHYo9PV0uDfTmN1OunNUcCRU-sJuR8RZz60PAXzfKybAdvuCxUedbt8aWtTjAdCCuO298TwT8zN1-T5EG3kgkOweg0DHGIbvP55IZbr6.DY_NR2Ar5Od663rj6tJQrGvKD7ZZKNfYYmcgpIQC8xxKfYt_U_DY2yP5Qjo4mTT5QX1BsT8rZoG4XL6mEukmryZZjzsLTJplePXO-8zNqrw5Q9tSMj_qTr1x9tqvZul3xg1sSxW9qx-9LdoDkY4QPSl81_4pqO24rM-8dQjPakb3dS5iC0.U1Yk0ZDqs2v4VnL30ZKGm1Yk0Zfqs2v4VnL30A-V5HcsP0KM5gK1n6KdpHdBmy-bIykV0ZKGujYzr0KWpyfqnWcv0AdY5HDsnHIxnH0krNtknjc1g1nsnHNxn1msnfKopHYs0ZFY5HDLn6K-pyfq0AFG5HcsP0KVm1Y3nHDYP1fsrjuxnH0snNtkg1Dsn-ts0Z7spyfqn0Kkmv-b5H00ThIYmyTqn0K9mWYsg100ugFM5H00TZ0qPWm1PHm1rj640A4vTjYsQW0snj0snj0s0AdYTjYs0AwbUL0qn0KzpWYs0Aw-IWdsmsKhIjYs0ZKC5H00ULnqn0KBI1Ykn0K8IjYs0ZPl5fK9TdqGuAnqTZnVUhC0IZN15Hnkn1fknHT4P1DvPHR1PW61P100ThNkIjYkPHRYP10LrHTkPjTY0ZPGujd9rAwBmhuWrj0snjDzrj0Y0AP1UHYsPbm3wWTsrH0srjwarDcz0A7W5HD0TA3qn0KkUgfqn0KkUgnqn0KlIjYs0AdWgvuzUvYqn7tsg1Kxn7ts0Aw9UMNBuNqsUA78pyw15HKxn7tsg1nkrjm4nNts0ZK9I7qhUA7M5H00uAPGujYknjT1P1fkrjcY0ANYpyfqQHD0mgPsmvnqn0KdTA-8mvnqn0KkUymqn0KhmLNY5H00uMGC5H00uh7Y5H00XMK_Ignqn0K9uAu_myTqnfK_uhnqn0KEIjYs0AqzTZfqnanscznsc100mLFW5HRdPj0Y%26word%3D%25E6%258B%2589%25E5%258B%25BE%25E7%25BD%2591%26ck%3D1701.10.72.227.558.354.602.254%26shh%%26sht%3D62095104_19_oem_dg%26us%3D1.0.1.0.1.301.0%26bc%3D110101; PRE_LAND=https%3A%2F%%2Flp%2Fhtml%%3Futm_source%3Dm_cf_cpc_baidu_pc%26m_kw%3Dbaidu_cpc_cd_e110f9_d2162e_%25E6%258B%2589%25E5%258B%25BE%25E7%25BD%2591; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1553064535,1554696044,1554707975; TG-TRACK-CODE=index_search; SEARCH_ID=16b25888bc6f489f981996ef505d6930; X_HTTP_TOKEN=3704e5535eab672a10080745514b2c7fac0430c282; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1554708001; LGRID=20190408152002-b9743b5b-59ce-11e9-9a84-525400f775ce", "X-Anit-Forge-Code":"0" , "X-Anit-Forge-Token":'', "X-Requested-With":'XMLHttpRequest' } def get_detail_page_url(): datas =[] url = '/jobs/' form_data = { "first":"faise", "pn":1, "kd":"python" } params = { 'city':'成都', 'needAddtionalResult':'false' } for pn in range(1,14): form_data['pn'] = pn response = (method='post',url=url,headers=headers,params = params,data = form_data) result = () result_list = result['content']['positionResult']['result'] for position in result_list: position_id = position['positionId'] detail_url = '/jobs/%'%position_id data = parse_detail_page(detail_url) (data) (2) return datas def parse_detail_page(url): resonse = (method='get',url=url,headers = headers) text = html = (text,parser=()) position_name = ('//span[@class="name"]/text()')[0].strip() detail_list = ('//dd[@class="job_request"]//span') salary = detail_list[0].xpath('text()')[0].strip() city = detail_list[1].xpath('text()')[0].strip() city = (r'[\s/]','',city) work_years = detail_list[2].xpath('text()')[0].strip() work_years = (r'[\s/]','',work_years) education = detail_list[3].xpath('text()')[0].strip() education = (r'[\s/]','',education) job_details = ''.join(('//div[@class="job-detail"]//p//text()')) data = { "position_name":position_name, "salay":salary, "city":city, "work_years":work_years, "education":education, "job_details":job_details } return data def main(): datas = get_detail_page_url() print(datas) if __name__ == '__main__': main()