Python下selenium的实战和普通爬虫的对比

"""普通爬取数据爬虫，只要有反爬，cookie就不是很稳定。并不利于数据爬取"""
import requests
import re
from lxml import etree


headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3554.0 Safari/537.36",
        "Referer": "https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput=",
        # Cookie需要时常换取
        "Cookie": "_ga=GA1.2.1553999204.1538311958; user_trace_token=20180930205504-0cebb367-c4b0-11e8-bb68-5254005c3644; "
                  "LGUID=20180930205504-0cebbcd1-c4b0-11e8-bb68-5254005c3644; showExpriedIndex=1; showExpriedCompanyHome=1; "
                  "showExpriedMyPublish=1; index_location_city=%E6%B7%B1%E5%9C%B3; sensorsdata2015jssdkcross=%7B%22distinct_"
                  "id%22%3A%22166811f974d15e-026ab47692a8d1-181c7151-2073600-166811f974e549%22%2C%22%24device_id%22%3A%2216681"
                  "1f974d15e-026ab47692a8d1-181c7151-2073600-166811f974e549%22%7D; LG_LOGIN_USER_ID=1d0d39f3227c1f914a3f9c4d95f"
                  "4816a5c6667141cc1313edac4603b4bd6d789; hasDeliver=6; _gid=GA1.2.2026255269.1540465512; WEBTJ-ID=2018102519420"
                  "2-166ab0808f9cb-06806b898438ec-181c7151-2073600-166ab0808fb7ef; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=15401"
                  "21809,1540210602,1540465512,1540467723; LGSID=20181025194505-6ab63d2a-d84b-11e8-8168-5254005c3644; PRE_UTM=m_cf_"
                  "cpt_baidu_pc; PRE_HOST=www.baidu.com; PRE_SITE=https%3A%2F%2Fwww.baidu.com%2Fs%3Fie%3Dutf-8%26f%3D8%26rsv_bp%3D0%2"
                  "6rsv_idx%3D1%26tn%3Dbaidu%26wd%3D%25E6%258B%2589%25E5%258B%25BE%25E7%25BD%2591%26rsv_pq%3D8d0dc05a0000aada%26rsv_t%"
                  "3D4664T41fswButqvfw6ZM6FGWfkWjtwR%252Fmpsskb6hctTVnUHewMo9o1%252BqRGk%26rqlang%3Dcn%26rsv_enter%3D1%26rsv_sug3%3D7%26r"
                  "sv_sug1%3D8%26rsv_sug7%3D100; PRE_LAND=https%3A%2F%2Fwww.lagou.com%2Flp%2Fhtml%2Fcommon.html%3Futm_source%3Dm_cf_cpt_baidu_pc;"
                  " _putrc=1D33894D7A6BEB76123F89F2B170EADC; JSESSIONID=ABAAABAAAGFABEF9CEC8B1F38F5075A286961D31667AC5C; login=true; unick=%E6%9D%A"
                  "8%E7%A6%B9; gate_login_token=b0629019d50bbe97eb829d61be9770ad4b570c1e68e239c68ae16cc71c68c808; _gat=1; Hm_lpvt_4233e74dff0ae5bd0a"
                  "3d81c6ccf756e6=1540469398; LGRID=20181025201301-5183464a-d84f-11e8-a347-525400f775ce; TG-TRACK-CODE=index_search; SEARCH_ID=06714"
                  "3e245964eb7af08d8c8d316cd44"
    }


def request_list_page():
    # 获取详情页面url
    url = "https://www.lagou.com/jobs/positionAjax.json?city=%E6%B7%B1%E5%9C%B3&needAddtionalResult=false"
    data = {
        "first": "false",
        "pn": 1,
        "kd": "Python"
    }
    for x in range(1, 31):
        data["pn"] = x
        rep = requests.post(url=url, headers=headers, data=data)
        # json方法，如果返回来的是json数据，自动转换为字典
        result = rep.json()
        # json在线解析分析数据格式
        positions = result["content"]["positionResult"]["result"]
        for position in positions:
            positionId = position["positionId"]
            # 找到详情页url，并传递给解析函数
            position_url = "https://www.lagou.com/jobs/{}.html".format(positionId)
            parse_position_detail(position_url)
            break
        break


def parse_position_detail(url):
    # 页面解析
    res = requests.get(url, headers=headers)
    text = res.text
    html = etree.HTML(text)
    position_depart = html.xpath("//div[@class='company']/text()")
    position_names = html.xpath("//span[@class='name']/text()")
    job_requests = html.xpath("//dd[@class='job_request']//span/text()")
    salary_span = re.sub(r"[\s/]", "", job_requests[0].strip())
    addr_span = re.sub(r"[\s/]", "", job_requests[1].strip())
    exper_span = re.sub(r"[\s/]", "", job_requests[2].strip())
    education_span = re.sub(r"[\s/]", "", job_requests[3].strip())
    full_span = re.sub(r"[\s/]", "", job_requests[4].strip())
    desc = "".join(html.xpath("//dd[@class='job_bt']//text()")).strip()
    print(position_depart, position_names, salary_span, addr_span, exper_span, education_span, full_span, desc)


if __name__ == '__main__':
    request_list_page()

View Code