利用xpath爬取招聘网的招聘信息

爬取招聘网的招聘信息：

import json
import random
import time


import pymongo
import re
import pandas as pd
import requests
from lxml import etree
import datetime

# 设置cookie中可变的值
now = datetime.datetime.now()
timeStamp = int(now.timestamp()*1000)
geshi = "%Y%m%d%H%M%S"
time1 = datetime.datetime.strftime(now,geshi)


# 设置mongodb
client = pymongo.MongoClient('localhost')
# 设置数据库名
db = client['lagou']
# 指定集合名
data_name = 'lagouData'
detail = 'detailData'

# 常量
CITY = '广州'
# 查询的岗位名称
POSITON_NAME = '数据挖掘'
# 想要爬取的总页面数
PAGE_SUN = 10
# 每页返回的职位数量
PAGE_SIZE = 15

# 匹配span[position()>3]：表示p标签下从第三个span开始匹配所以
# //dd[@class='job_request']/p/span[position()>3]

# index_url = 'https://m.lagou.com/search.json?city={}&positionName={}&pageNo={}&pageSize=15'
# index页地址url
index_url = 'https://m.lagou.com/search.json?city={}&positionName={}&pageNo={}&pageSize={}'
# 详情页地址url
detail_url = 'https://m.lagou.com/jobs/{}.html'
# 浏览代理用户
user_agents = [
    "Mozilla/5.0 (iPhone 84; CPU iPhone OS 10_3_3 like Mac OS X) AppleWebKit/603.3.8 (KHTML, like Gecko) Version/10.0 MQQBrowser/7.8.0 Mobile/14G60 Safari/8536.25 MttCustomUA/2 QBWebViewType/1 WKType/1",
    "Mozilla/5.0 (Linux; Android 7.0; STF-AL10 Build/HUAWEISTF-AL10; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/53.0.2785.49 Mobile MQQBrowser/6.2 TBS/043508 Safari/537.36 V1_AND_SQ_7.2.0_730_YYB_D QQ/7.2.0.3270 NetType/4G WebP/0.3.0 Pixel/1080",
    "Mozilla/5.0 (iPhone; CPU iPhone OS 10_3_3 like Mac OS X) AppleWebKit/603.3.8 (KHTML, like Gecko) Mobile/14G60 MicroMessenger/6.5.18 NetType/WIFI Language/en",
    "Mozilla/5.0 (Linux; Android 5.1.1; vivo Xplay5A Build/LMY47V; wv) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/48.0.2564.116 Mobile Safari/537.36 T7/9.3 baiduboxapp/9.3.0.10 (Baidu; P1 5.1.1)",
    "Mozilla/5.0 (Linux; U; Android 7.0; zh-cn; STF-AL00 Build/HUAWEISTF-AL00) AppleWebKit/537.36 (KHTML, like Gecko)Version/4.0 Chrome/37.0.0.0 MQQBrowser/7.9 Mobile Safari/537.36",
    "Mozilla/5.0 (Linux; Android 6.0; LEX626 Build/HEXCNFN5902606111S) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/35.0.1916.138 Mobile Safari/537.36 T7/7.4 baiduboxapp/8.3.1 (Baidu; P1 6.0)",
    "Mozilla/5.0 (iPhone 92; CPU iPhone OS 10_3_2 like Mac OS X) AppleWebKit/603.2.4 (KHTML, like Gecko) Version/10.0 MQQBrowser/7.7.2 Mobile/14F89 Safari/8536.25 MttCustomUA/2 QBWebViewType/1 WKType/1",
    "Mozilla/5.0 (Linux; U; Android 7.0; zh-CN; ZUK Z2121 Build/NRD90M) AppleWebKit/537.36 (KHTML, like Gecko) Version/4.0 Chrome/40.0.2214.89 UCBrowser/11.6.8.952 Mobile Safari/537.36"]


# index页面
def index_fn():
    user_agent=random.choice(user_agents)
    headers = {
        "Accept": "application/json",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Host": "m.lagou.com",
        #
        "Cookie": "_ga=GA1.2.841469794.1541152606; user_trace_token=20181102175657-a2701865-de85-11e8-8368-525400f775ce; LGUID=20181102175657-a2701fbd-de85-11e8-8368-525400f775ce; index_location_city=%E5%B9%BF%E5%B7%9E; _gid=GA1.2.311675459.1542615716; _ga=GA1.3.841469794.1541152606; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1542634073,1542634080,1542634122,1542634128; JSESSIONID=ABAAABAAAGCABCC1B87E5C12282CECED77A736D4CD7FA8A; X_HTTP_TOKEN=aae2d9e96d6a68f72d98ab409a933460; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%221672c5c65c01c7-0e8e56366a6cce-3a3a5c0e-2073600-1672c5c65c3bf%22%2C%22%24device_id%22%3A%221672c5c65c01c7-0e8e56366a6cce-3a3a5c0e-2073600-1672c5c65c3bf%22%7D; sajssdk_2015_cross_new_user=1; _gat=1; LGSID=20181119231628-167f7db1-ec0e-11e8-a76a-525400f775ce; PRE_UTM=; PRE_HOST=; PRE_SITE=https%3A%2F%2Fm.lagou.com%2Fsearch.html; PRE_LAND=https%3A%2F%2Fm.lagou.com%2Fjobs%2F5219979.html; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6={timeStamp}; LGRID={time}-1c458fde-ec0e-11e8-895f-5254005c3644".format(
            timeStamp=timeStamp, time=time1),
        "Referer": "https://m.lagou.com/search.html",
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36",
        "X-Requested-With": "XMLHttpRequest",
    }
    for i in range(PAGE_SIZE):
        proxies = {'HTTP': '171.37.164.78:8123'}
        response = requests.get(index_url.format(CITY, POSITON_NAME, i, PAGE_SIZE), headers=headers,proxies=proxies).content.decode()
        content = json.loads(response)
        # print('content', content)
        if content:
            try:
                result = content['content']['data']['page']['result']
                for item in result:
                    # print(type(item),item)
                    # print(item['positionId'])
                    data = {
                        'positionId': item['positionId'],
                        'positionName': item['positionName'],
                        'city': item['city'],
                        'createTime':item['createTime'],
                        'companyId': item['companyId'],
                        'companyLogo': item['companyLogo'],
                        'companyName': item['companyName'],
                        'companyFullName': item['companyFullName'],
                    }
                    time.sleep(0.5)
                    # db['lagouData'].insert(data)
                    yield data
            except Exception as e:
                print('爬取index页出错', e)
        else:
            time.sleep(10)
            print('重新加载')
            # except Exception as e:
            #     print('爬取index页出错', e)


# 详情页：
def detail_d(positionId):
    # 随机获取代理对象
    user_agent = random.choice(user_agents)
    headers = {
        "Accept": "application/json",
        "Accept-Encoding": "gzip, deflate, br",
        "Accept-Language": "zh-CN,zh;q=0.9",
        "Connection": "keep-alive",
        "Host": "m.lagou.com",
        #
        "Cookie": "_ga=GA1.2.841469794.1541152606; user_trace_token=20181102175657-a2701865-de85-11e8-8368-525400f775ce; LGUID=20181102175657-a2701fbd-de85-11e8-8368-525400f775ce; index_location_city=%E5%B9%BF%E5%B7%9E; _gid=GA1.2.311675459.1542615716; _ga=GA1.3.841469794.1541152606; Hm_lvt_4233e74dff0ae5bd0a3d81c6ccf756e6=1542634073,1542634080,1542634122,1542634128; JSESSIONID=ABAAABAAAGCABCC1B87E5C12282CECED77A736D4CD7FA8A; X_HTTP_TOKEN=aae2d9e96d6a68f72d98ab409a933460; sensorsdata2015jssdkcross=%7B%22distinct_id%22%3A%221672c5c65c01c7-0e8e56366a6cce-3a3a5c0e-2073600-1672c5c65c3bf%22%2C%22%24device_id%22%3A%221672c5c65c01c7-0e8e56366a6cce-3a3a5c0e-2073600-1672c5c65c3bf%22%7D; sajssdk_2015_cross_new_user=1; _gat=1; LGSID=20181119231628-167f7db1-ec0e-11e8-a76a-525400f775ce; PRE_UTM=; PRE_HOST=; PRE_SITE=https%3A%2F%2Fm.lagou.com%2Fsearch.html; PRE_LAND=https%3A%2F%2Fm.lagou.com%2Fjobs%2F5219979.html; Hm_lpvt_4233e74dff0ae5bd0a3d81c6ccf756e6={timeStamp}; LGRID={time}-1c458fde-ec0e-11e8-895f-5254005c3644".format(
            timeStamp=timeStamp, time=time1),
        "Referer": "https://m.lagou.com/search.html",
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36",
        "X-Requested-With": "XMLHttpRequest",
    }
    response = requests.get(detail_url.format(positionId), headers=headers).content.decode()

    xml = etree.HTML(response)
    title = xml.xpath('''//div[@class='postitle']/h2/text()''')
    job_details = xml.xpath('''//div[@class='detail']/div[1]//span/span/text()''')
    job_detail = str(job_details).replace(r'
', '').replace(' ', '')
    work_detial = xml.xpath('''//div[@class='content']//p/text()''')
    company_img = xml.xpath('''//div[@class='content']//p/text()''')
    company_infors = xml.xpath(
        '''//div[@class='company activeable']/div/div/h2/text()|//div[@class='dleft']/p/text()''')
    company_infor = str(company_infors).strip().replace(r'
', '').replace(' ', '')
    detail_datas = {
        'title': title,
        'job_detail': job_detail,
        'work_detial': work_detial,
        'company_img': company_img,
        'company_infor': company_infor
    }
    return detail_datas


# 保存到mongodb
def save_to_mongodb(data, detail_datas, positionId):
    # if db[data_name].update({'positionId': positionId}, {'$set': data}, True):
    #     print('update to Mongo', data['positionId'])

    db['lagouData'].insert(data)
    db['detailDta'].insert(detail_datas)
    print('成功存入mongodb')


# 保存为csv文件
def save_to_csv():
    item_list = []
    for item in index_fn():
        item_list.append(item)
        print('123456', item)
    # print('详情列', item_list)
    # item_list是一个列表，里面装很多字典类似{'positionId': 4102483, 'positionName': '数据挖掘工程师', 'city': '广州',...
    datas = pd.DataFrame(item_list, columns=["positionId", "positionName", "city", "createTime", "salary", "companyId",
                                             "companyLogo", "companyName", "companyFullName"])

    datas.to_csv('./static/lagou.csv')
    print('保存为csv文件成功')


def run():
    # 保存为csv文件
    # proxies=get_ip()
    # for i in proxies:
    data = index_fn()
    save_to_csv()
    for item in data:
        print('data', item)
        positionId = item['positionId']
        print(positionId)
        # 调用详情页函数
        detail_datas = detail_d(positionId)
        # 保存详情页和主页的数据到mongodb
        save_to_mongodb(data, detail_datas, positionId)


if __name__ == '__main__':
    run()

预防反爬虫措施：

1.用户代理变换设置

2.不同ip代理的设置

3.设置用户cookie变化的信息

列举一下获取网络免费ip代理，并验证其是否可用的代码：

import requests
import re
import telnetlib
from lxml import etree
import time
def get_ip():
    headers = {
        "User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36",
    }
    url = "http://www.xicidaili.com/nn/"
    res = requests.get(url,headers=headers)
    content = res.content.decode()

    # 调用lxml中的etree库便于用xpath获取html中的文本
    xml = etree.HTML(content)
    # 以下为xpath语法
    # //tr[@class='odd']//td[2]//text()  ip
    # //tr[@class='odd']//td[3]//text() port 端口
    # //tr[@class='odd']//td[6]//text()  type 类型
    ip_list = xml.xpath("//tr[@class='odd']//td[2]//text()")
    port_list = xml.xpath("//tr[@class='odd']//td[3]//text()")
    type_list = xml.xpath("//tr[@class='odd']//td[6]//text()")
    if len(ip_list) != 0:
        for ip,port,type in zip(ip_list,port_list,type_list):
            proxies = {
                type:"{}:{}".format(ip,port)
            }
            try:
                telnetlib.Telnet(ip, port=port, timeout=10)
            except Exception:
                print("不能使用该{}".format(proxies))
            else:
                print('可以使用该{}'.format(proxies))
                yield proxies
        get_ip()
    else:
        time.sleep(1)
        get_ip()


    # content= res.content.decode()
    # print(content)



# if __name__ == '__main__':
#     ip = get_ip()
    # print(ip)
    # for i in ip:
    #     pass
        # yield i
        # print('getip,getip',i)