最近从一个小破网站爬取了四百多万条数据,做了一个数据分析的工作(就是画几张破图)。
利用post请求爬取分页数据
代码如下
import random
import requests
import pandas as pd
from bs4 import BeautifulSoup
from lxml import etree
import time
#import pymysql
from sqlalchemy import create_engine
from urllib.parse import urlencode # 编码 URL 字符串
start_time = time.time() #计算程序运行时间
def new():
session = requests.Session()# 创建一个新会话
return session
def get_one_page(start_begin,session):
for i in range(start_begin,8047):#代表着从start_begin开始,到8046页结束
time.sleep(1)#进程睡眠一秒
agents = [ #各种浏览器头代理
"Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:17.0; Baiduspider-ads) Gecko/17.0 Firefox/17.0",
"Mozilla/5.0 (Linux; U; Android 2.3.6; en-us; Nexus S Build/GRK39F) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Avant Browser/1.2.789rel1 (http://www.avantbrowser.com)",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/532.5 (KHTML, like Gecko) Chrome/4.0.249.0 Safari/532.5",
"Mozilla/5.0 (Windows; U; Windows NT 5.2; en-US) AppleWebKit/532.9 (KHTML, like Gecko) Chrome/5.0.310.0 Safari/532.9",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US) AppleWebKit/534.7 (KHTML, like Gecko) Chrome/7.0.514.0 Safari/534.7",
"Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/9.0.601.0 Safari/534.14",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.14 (KHTML, like Gecko) Chrome/10.0.601.0 Safari/534.14",
"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.20 (KHTML, like Gecko) Chrome/11.0.672.2 Safari/534.20",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.27 (KHTML, like Gecko) Chrome/12.0.712.0 Safari/534.27",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.24 Safari/535.1",
"Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.2 (KHTML, like Gecko) Chrome/15.0.874.120 Safari/535.2",
"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.7 (KHTML, like Gecko) Chrome/16.0.912.36 Safari/535.7",
"Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9b4) Gecko/2008030317 Firefox/3.0b4",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.9.0.10) Gecko/2009042316 Firefox/3.0.10",
"Mozilla/5.0 (Windows; U; Windows NT 6.0; en-GB; rv:1.9.0.11) Gecko/2009060215 Firefox/3.0.11 (.NET CLR 3.5.30729)",
"Mozilla/5.0 (Windows; U; Windows NT 6.0; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6 GTB5",
"Mozilla/5.0 (Windows; U; Windows NT 5.1; tr; rv:1.9.2.8) Gecko/20100722 Firefox/3.6.8 ( .NET CLR 3.5.30729; .NET4.0E)",
"Mozilla/5.0 (Windows; U; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727; BIDUBrowser 7.6)",
"Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko",
"Mozilla/5.0 (Windows NT 6.3; WOW64; rv:46.0) Gecko/20100101 Firefox/46.0",
"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.99 Safari/537.36",
"Mozilla/5.0 (Windows NT 6.3; Win64; x64; Trident/7.0; Touch; LCJB; rv:11.0) like Gecko",
"Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
"Mozilla/5.0 (Windows NT 5.1; rv:5.0) Gecko/20100101 Firefox/5.0",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0a2) Gecko/20110622 Firefox/6.0a2",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:7.0.1) Gecko/20100101 Firefox/7.0.1",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:2.0b4pre) Gecko/20100815 Minefield/4.0b4pre",
"Mozilla/4.0 (compatible; MSIE 5.5; Windows NT 5.0 )",
"Mozilla/4.0 (compatible; MSIE 5.5; Windows 98; Win 9x 4.90)",
"Mozilla/5.0 (Windows; U; Windows XP) Gecko MultiZilla/1.6.1.0a",
"Mozilla/2.02E (Win95; U)",
"Mozilla/3.01Gold (Win95; I)",
"Mozilla/4.8 [en] (Windows NT 5.1; U)",
"Mozilla/5.0 (Windows; U; Win98; en-US; rv:1.4) Gecko Netscape/7.1 (ax)",
"HTC_Dream Mozilla/5.0 (Linux; U; Android 1.5; en-ca; Build/CUPCAKE) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
"Mozilla/5.0 (hp-tablet; Linux; hpwOS/3.0.2; U; de-DE) AppleWebKit/534.6 (KHTML, like Gecko) wOSBrowser/234.40.1 Safari/534.6 TouchPad/1.0",
"Mozilla/5.0 (Linux; U; Android 1.5; en-us; sdk Build/CUPCAKE) AppleWebkit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
"Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 2.2; en-us; Nexus One Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 1.5; en-us; htc_bahamas Build/CRB17) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
"Mozilla/5.0 (Linux; U; Android 2.1-update1; de-de; HTC Desire 1.19.161.5 Build/ERE27) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 2.2; en-us; Sprint APA9292KT Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 1.5; de-ch; HTC Hero Build/CUPCAKE) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
"Mozilla/5.0 (Linux; U; Android 2.2; en-us; ADR6300 Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 2.1; en-us; HTC Legend Build/cupcake) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 1.5; de-de; HTC Magic Build/PLAT-RC33) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1 FirePHP/0.3",
"Mozilla/5.0 (Linux; U; Android 1.6; en-us; HTC_TATTOO_A3288 Build/DRC79) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
"Mozilla/5.0 (Linux; U; Android 1.0; en-us; dream) AppleWebKit/525.10 (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
"Mozilla/5.0 (Linux; U; Android 1.5; en-us; T-Mobile G1 Build/CRB43) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari 525.20.1",
"Mozilla/5.0 (Linux; U; Android 1.5; en-gb; T-Mobile_G2_Touch Build/CUPCAKE) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
"Mozilla/5.0 (Linux; U; Android 2.0; en-us; Droid Build/ESD20) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 2.2; en-us; Droid Build/FRG22D) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 2.0; en-us; Milestone Build/ SHOLS_U2_01.03.1) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 2.0.1; de-de; Milestone Build/SHOLS_U2_01.14.0) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/525.10 (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
"Mozilla/5.0 (Linux; U; Android 0.5; en-us) AppleWebKit/522 (KHTML, like Gecko) Safari/419.3",
"Mozilla/5.0 (Linux; U; Android 1.1; en-gb; dream) AppleWebKit/525.10 (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
"Mozilla/5.0 (Linux; U; Android 2.0; en-us; Droid Build/ESD20) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 2.1; en-us; Nexus One Build/ERD62) AppleWebKit/530.17 (KHTML, like Gecko) Version/4.0 Mobile Safari/530.17",
"Mozilla/5.0 (Linux; U; Android 2.2; en-us; Sprint APA9292KT Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 2.2; en-us; ADR6300 Build/FRF91) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 2.2; en-ca; GT-P1000M Build/FROYO) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1",
"Mozilla/5.0 (Linux; U; Android 3.0.1; fr-fr; A500 Build/HRI66) AppleWebKit/534.13 (KHTML, like Gecko) Version/4.0 Safari/534.13",
"Mozilla/5.0 (Linux; U; Android 3.0; en-us; Xoom Build/HRI39) AppleWebKit/525.10 (KHTML, like Gecko) Version/3.0.4 Mobile Safari/523.12.2",
"Mozilla/5.0 (Linux; U; Android 1.6; es-es; SonyEricssonX10i Build/R1FA016) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1",
"Mozilla/5.0 (Linux; U; Android 1.6; en-us; SonyEricssonX10i Build/R1AA056) AppleWebKit/528.5 (KHTML, like Gecko) Version/3.1.2 Mobile Safari/525.20.1"
]
url = "http:///pub/GongShiSearch?pageIndex=%s"%(str(i)) #这里填自己的网址,pageindex代表页码,在network里有这项
headers = { #按F12 点击network 查看请求头
'Accept': '*/*',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'zh-CN,zh;q=0.9,en-US;q=0.8,en;q=0.7',
'Content-Length': '401',
'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8',
'Cookie':'__RequestVerificationToken_Lw__=wPRuBTxCRUDr+nWCcdSXXVGG80WumYmsWWN/neCQtForjKZojzUEBxkn3jAkpLUlXXLRQhgedgODZQAt9YnqCPLb3PT0iqLIlse50W4z40NzTvU/AHtiD1yPxadHEeqawnm/SNufTovg9+q0iqryiLDomJOC2u9OCSVMW6cMkY8=',
'Host':'',
'Origin':'',
'Proxy-Connection':'keep-alive',
'Referer':'',
'User-Agent': random.choice(agents),
'X-Requested-With': 'XMLHttpRequest'
}
data = {'__RequestVerificationToken':'oYGG20C3qFbyQYgpdGFMUeIskiMmeoPKbEAOMmV2fQ8BRC6KCgymd1dCNLqsxkAvXJCyeiBgQR8fdEUS4f08i654jEMYJsCNWJEljcQbf9AjLN2pTnA0X3+hndi2V3vR2kHx3/NYkKZwsXXhWigvwLqdfjGTVfQB/e6HQAMiavI=',
'YearNum': '2018',
'areaName': '',
'AreaCode': '' ,
'qy': '',
'n': '' ,
'JiJuLeiXing': '',
'JiJuLeiXingCode': '',
'FactoryName': '',
'BusinessName': '' ,
'ChuCBH': '',
'StartGJRiQi': '2018-01-01',
'EndGJRiQi': '2018-12-31',
'StateValue': '',
'StateName': '' } #输入查询的条件参数
while True:
try:
response = session.post(url, data=data, headers=headers)# 进行post请求
print(i,response.status_code) # 返回当前页码和状态码
break
except Exception:
session.close() #关闭会话
print('Sleep 5s.n')
time.sleep(5)#进程休眠5s
session = new() #创建新会话
get_one_page(i,session) #递归调用
soup = BeautifulSoup(response.text,'lxml') #解析返回的文章内容
try:
content = soup.select('table')[0] #[0]将返回的list改为bs4类型 #在返回的html网页里选择table类型的
except Exception:
#print(soup)
session.close()
print('nSleep 5s.n')
time.sleep(5)
session = new()
get_one_page(i,session)
tbl = pd.read_html(content.prettify(),header = 0) #解析html内容
if i==1:
tbl[0].head(15).to_csv(r'shandong_2018_2018_2.csv',mode='a+',encoding='gb18030', header=1,index=0) #将table里的数据存入csv
else:
tbl[0].head(15).to_csv(r'shandong_2018_2018_2.csv',mode='a+',encoding='gb18030', header=0,index=0)
# # 单进程
if __name__ == '__main__':
session= new()
get_one_page(4024,session) #代表从4024页开始
#main(40)
endtime = time.time()-start_time
print('程序运行了%.2f秒' %endtime)
# 多进程# from multiprocessing import Pool
# if __name__ == '__main__':
# pool = Pool(4)
# pool.map(main, [i for i in range(1,178)])
#共有178页# endtime = time.time()-start_time# print('程序运行了%.2f秒' %(time.time()-start_time))
注释写的比较详细,看注释就行了