python 爬虫的初步实践

时间:2019-10-11
本文章向大家介绍python 爬虫的初步实践,主要包括python 爬虫的初步实践使用实例、应用技巧、基本知识点总结和需要注意事项,具有一定的参考价值,需要的朋友可以参考一下。

简介

我的sisiter,想要我爬一些试题给她。有80套,她不想手工点,所以,我来了,比较简单的网站。所以没有费很大的力气。期间参考了一系列的网站,都没有记录下来。

code

#!/usr/bin/env python
#coding=utf-8

import pdfkit
import time
import requests
import sys
import urllib2
import re

def get_hiddenvalue(url):
    request=urllib2.Request(url)
    reponse=urllib2.urlopen(request)
    resu=reponse.read()
    VIEWSTATE=re.findall(r'<input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="(.*?)" />',resu, re.I)
    EVENTVALIDATION =re.findall(r'input type="hidden" name="__EVENTVALIDATION" id="__EVENTVALIDATION" value="(.*?)" />', resu,re.I)
    return VIEWSTATE[0],EVENTVALIDATION[0]

def get_hiddenvalue_string(myStr):
    VIEWSTATE=re.findall(r'<input type="hidden" name="__VIEWSTATE" id="__VIEWSTATE" value="(.*?)" />',myStr, re.I)
    EVENTVALIDATION =re.findall(r'input type="hidden" name="__EVENTVALIDATION" id="__EVENTVALIDATION" value="(.*?)" />', myStr,re.I)
    return VIEWSTATE[0],EVENTVALIDATION[0]

reload(sys)
sys.setdefaultencoding( "utf-8" )
data = {
    'cid':'1',
    'pid':'5'
}
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36',
}
options = {
    'page-size': 'A4',
    'margin-top': '0mm',
    'margin-right': '0mm',
    'margin-bottom': '0mm',
    'margin-left': '0mm',
    # 'orientation':'Landscape',#横向
    'encoding': "UTF-8",
    'no-outline': None,
      # 'footer-right':'[page]' 设置页码
}
myMap=["UniversityPsychology","HigherEducationRegulations","HigherEducation","TeacherEthics"]
confg = pdfkit.configuration(wkhtmltopdf='/usr/local/bin/wkhtmltopdf')
for i in range(4):
    for j in range(20):
        data['cid'] = str(i+1)
        data['pid'] = str(j+1)
        url='http://zjzx.zjnu.edu.cn/test/Default.aspx?cid='+str(i+1)+'&pid='+str(j+1)
        #response = requests.post(url=url,data=data,headers=headers)
        myStr = myMap[i]+'_'+'exam'+str(j+1)+'.pdf'
        #response.encoding = 'utf-8'
        myStr1 = myMap[i]+'_'+'exam'+str(j+1)+'.html'

        data['Button1'] = '提交并查看单选题答案'
        data['drop1']= '1'
        data['drop2']='1'
        data['__VIEWSTATE'],data['__EVENTVALIDATION'] = get_hiddenvalue(url) # 请查阅__VIEWSTATE __EVENTVALIDATION 一个是把所有的按键信息编码上传,一个是加密用的
        response = requests.post(url=url,data=data,headers=headers)
        responseReturn = response.text
        time.sleep(3)
        del data['Button1']
        data['__VIEWSTATE'],data['__EVENTVALIDATION']=get_hiddenvalue_string(responseReturn)
        data['Button2']='提交并查看多选题答案'
        response = requests.post(url=url,data=data,headers=headers)
        responseReturn = response.text

        time.sleep(3)
        del data['Button2']
        data['__VIEWSTATE'],data['__EVENTVALIDATION']=get_hiddenvalue_string(responseReturn)
        data['Button3']='提交并查看判断题答案'
        response = requests.post(url=url,data=data,headers=headers)
        responseReturn = response.text
        del data['Button3']
        with open(myStr1,'a') as file:
            file.write(responseReturn)
                
        with open(myStr1, 'r') as file:
            answer = file.read()
            pdfkit.from_string(answer, myStr,configuration=confg,options=options)
        
        #pdfkit.from_url(url, myStr,configuration=confg)

原文地址:https://www.cnblogs.com/eat-too-much/p/11655176.html