這幾天在學(xué)爬蟲，就想著嘗試爬取一下網(wǎng)站，一下是爬取51job的過程

分析網(wǎng)站

image.png

這是首頁，大家可以嘗試各種方法抓取接口。

查看變化，嘗試直接在get頭改變信息

[圖片上傳中...(image.png-c093dd-1589098280977-0)]

image.png

由此看到，搜索接口

在查看網(wǎng)頁第一，二頁

image.png

由此，可以看到頁數(shù)接口

獲取信息

比如職位信息：由于我最近在學(xué)xpath，所以用xpath來定點(diǎn)

image.png

右鍵復(fù)制xpath，就可以拿到想要的節(jié)點(diǎn)了，但需要注意的是，要循環(huán)的話就不能用原始的xpath，可以自行改一下。

獻(xiàn)上代碼

image.png

不多bb，直接上代碼

import random
from lxml import etree
import requests
import re
import pymysql
?
# 使用隨機(jī)agent
def rand_user():
 ua_list = [
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36 OPR/26.0.1656.60",
 "Opera/8.0 (Windows NT 5.1; U; en)",
 "Mozilla/5.0 (Windows NT 5.1; U; en; rv:1.8.1) Gecko/20061208 Firefox/2.0.0 Opera 9.50",
 "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; en) Opera 9.50",
 "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
 "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2 ",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.71 Safari/537.36",
 "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
 "Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36",
 "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/2.0 Safari/536.11",
 "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
 "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; LBBROWSER)",
 "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E; LBBROWSER)",
 "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)",
 "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
 "Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0",
 "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; SE 2.X MetaSr 1.0)",
 ]
 ua = random.choice(ua_list)
 headers = {
 "User-Agent": ua
 }
 return headers
?
?
# 使用代理ip
def proxy():
 proxy_list = [
 {
 "HTTP": "92.247.142.14:53281",
 },
 {
 "HTTP": "203.150.160.157:8080",
 },
 {
 "HTTP": "91.211.107.204:41258",
 }
 ]
 pr = random.choice(proxy_list)
 return pr
?
?
?
?
# 獲取崗位數(shù)據(jù)
def get_detail():
 work = input("你想要的職位")
 page = 1
 url = "https://search.51job.com/list/000000,000000,0000,00,9,99,{},2,{}.html?lang=c&stype=&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&providesalary=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare=".format(work,page)
 response = requests.get(url, headers=rand_user(), proxies=proxy())
 content = response.content.decode('gbk')
 # 獲取最后一頁
 mytree = etree.HTML(content)
 job_page = mytree.xpath('//*[@id="resultList"]/div[55]/div/div/div/span[1]/text()')
 job_page_str = str(job_page)
 num=re.findall(r'\d+', job_page_str)
 num1 = int(num[0])
 # print(num1)
?
 # 翻頁爬
 for i in range(1, num1+1):
?
 url +=  "https://search.51job.com/list/000000,000000,0000,00,9,99,{},2,{}.html?lang=c&stype=&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&providesalary=99&lonlat=0%2C0&radius=-1&ord_field=0&confirmdate=9&fromType=&dibiaoid=0&address=&line=&specialarea=00&from=&welfare=".format(work,i)
?
 try:
 # 先獲取頁面數(shù)據(jù)
 response = requests.get(url, headers=rand_user(), proxies=proxy())
 content = response.content.decode('gbk')
?
 # 使用xpath
 mytree = etree.HTML(content)
 job_list = mytree.xpath('//*[@id="resultList"]/div[@class="el"]')
 # print(job_list)
 # 獲取當(dāng)前頁的相關(guān)數(shù)據(jù)
 for job in job_list:
 job_name = job.xpath('./p/span/a/text()')[0]
 # print(job_name)
 # 公司
 job_company = job.xpath('./span/a/text()')[0]  # //*[@id="resultList"]/div[5]/span[1]/a
 # print(job_company)
 # 城市
 job_city = job.xpath('./span/text()')[0]
 # print(job_city)
 # 薪資
 job_salary = job.xpath('./span/text()')[1]
 # print(job_salary)
 job_salary1 = job.xpath('./span[@class="t5"]/text()')[0]
 # print(job_salary1)
 job_url = job.xpath('./p/span/a/@href')[0]
 # print(job_url)
 if job_salary != job_salary1:
 pass
 else:
 job_salary = "面議"
 str_job_name = job_name.strip()
 str_job_company=job_company.strip()
 str_job_city=job_city.strip()
 str_job_salary=job_salary.strip()
 str_job_url=job_url.strip()
?
 # 存入數(shù)據(jù)庫
 sql = 'insert into job_table values(null,"%s", "%s", "%s", "%s", "%s")'%(str_job_name, str_job_company, str_job_city, str_job_salary,str_job_url)
?
 cursor.execute(sql)
 db.commit()
 except Exception as e:
 pass
 print("*" * 40)
 print("%s 第%d頁 爬取異常" % (url, i))
 print(e)
 print("*" * 40)
?
?
if __name__ == '__main__':
 # 連接MySQL
 db = pymysql.connect(
 host="localhost",
 port=3306,
 user="root",
 password="123123",
 database="job",
 charset="utf8"
 )
 cursor = db.cursor()
 get_detail()
 cursor.close()
 db.close()