关于#python#的问题，帮写爬虫

帮忙写个python爬数据，内容在网盘里面，请你吃个饭。
写好直接私发给我，能用我马上结题，我选最快且能用的那个发截图到楼里，绝不白piao
这要这个class的，旁边有个很相似的class只要td class="feedbackObj" 的
链接: https://pan.baidu.com/s/1uPfhHcttsc07gzF0OCyPJA?pwd=q5g8 提取码: q5g8 复制这段内容后打开网盘

马上写

爬虫写在哪里
我刚刚好有3个
爬虫1

#encoding=utf-8
import urllib2

import re


class neihanba():
  def spider(self):
    '''
    爬虫的主调度器
    '''
    isflow=True#判断是否进行下一页
    page=1
    while isflow:
      url="http://www.neihanpa.com/article/list_5_"+str(page)+".html"
      html=self.load(url)
      self.deal(html,page)
      panduan=raw_input("是否继续(y/n)!")
      if panduan=="y":
        isflow=True
        page+=1
      else:
        isflow=False
  def load(self,url):
    '''
    针对url地址进行全部爬去
    :param url: url地址
    :return: 返回爬去的内容
    '''
    header = {
      "User-Agent": " Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36"
    }
    request = urllib2.Request(url, headers=header)
    response = urllib2.urlopen(request)
    html = response.read()
    return html
  def deal(self,html,page):
    '''
    对之前爬去的内容进行正则匹配，匹配出标题和正文内容
    :param html:之前爬去的内容
    :param page: 正在爬去的页码
    '''
    parrten=re.compile('<li class="piclist\d+">(.*?)</li>',re.S)
    titleList=parrten.findall(html)
    for title in titleList:
      parrten1=re.compile('<a href="/article/\d+.html" rel="external nofollow" >(.*)</a>')
      ti1=parrten1.findall(title)
      parrten2=re.compile('<div class="f18 mb20">(.*?)</div>',re.S)
      til2=parrten2.findall(title)
      for t in ti1:
        tr=t.replace("<b>","").replace("</b>","")
        self.writeData(tr,page)
      for t in til2:
        tr=t.replace("<p>","").replace("</p>","").replace("<br>","").replace("<br />","").replace("&ldquo","\"").replace("&rdquo","\"")
        self.writeData(tr,page)
  def writeData(self,context,page):
    '''
    将最终爬去的内容写入文件中
    :param context: 匹配好的内容
    :param page: 当前爬去的页码数
    '''
    fileName = "di" + str(page) + "yehtml.txt"
    with open(fileName, "a") as file:
      file.writelines(context + "\n")
if __name__ == '__main__':
  n=neihanba()
  n.spider()

爬虫2

#encoding=utf-8
import urllib
import urllib2

import re


class zhiLian():
  def spider(self,position,workPlace):
    '''
    爬虫的主调度器
    :param position: 职位
    :param workPlace: 工作地点
    '''
    url="http://sou.zhaopin.com/jobs/searchresult.ashx?"
    url+=urllib.urlencode({"jl":workPlace})
    url+="&"
    url+=urllib.urlencode({"kw":position})
    isflow=True#是否进行下一页的爬去
    page=1
    while isflow:
      url+="&"+str(page)
      html=self.load(url)
      self.deal1(html,page)
      panduan = raw_input("是否继续爬虫下一页(y/n)!")
      if panduan == "y":
        isflow = True
        page += 1
      else:
        isflow = False
  def load(self,url):
    '''
    针对url地址进行全部爬去
    :param url: url地址
    :return: 返回爬去的内容
    '''
    header = {
      "User-Agent": " Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36"
    }
    request = urllib2.Request(url, headers=header)
    response = urllib2.urlopen(request)
    html = response.read()
    return html
  def deal1(self,html,page):
    '''

    对之前爬去的内容进行正则匹配，匹配职位所对应的链接
    :param html:之前爬去的内容
    :param page: 正在爬去的页码
    '''
    parrten=re.compile('<a\s+style="font-weight:\s+bold"\s+par="ssidkey=y&amp;ss=\d+&amp;ff=\d+&amp;sg=\w+&amp;so=\d+"\s+href="(.*?)" rel="external nofollow" target="_blank">.*?</a>',re.S)
    til=parrten.findall(html)#爬去链接
    for t in til:
      self.deal2(t,page)
  def deal2(self,t,page):
    '''
    进行二次爬虫，然后在新的页面中对公司、薪资、工作经验进行匹配
    :param t: url地址
    :param page: 当前匹配的页数
    '''
    html=self.load(t)#返回二次爬虫的内容
    parrten1=re.compile('<a\s+onclick=".*?"\s+href=".*?" rel="external nofollow" \s+target="_blank">(.*?)\s+.*?<img\s+class=".*?"\s+src=".*?"\s+border="\d+"\s+vinfo=".*?"></a>',re.S)
    parrten2=re.compile('<li><span>职位月薪：</span><strong>(.*?)&nbsp;<a.*?>.*?</a></strong></li>',re.S)
    parrent3=re.compile('<li><span>工作经验：</span><strong>(.*?)</strong></li>',re.S)
    til1=parrten1.findall(html)
    til2=parrten2.findall(html)
    til3=parrent3.findall(html)
    str=""
    for t in til1:
      t=t.replace('<img title="专属页面" src="//img03.zhaopin.cn/2012/img/jobs/icon.png" border="0" />',"")
      str+=t
      str+="\t"
    for t in til2:
      str+=t
      str += "\t"
    for t in til3:
      str+=t
    self.writeData(str,page)
  def writeData(self,context,page):
    '''
    将最终爬去的内容写入文件中
    :param context: 匹配好的内容
     :param page: 当前爬去的页码数
    '''
    fileName = "di" + str(page) + "yehtml.txt"
    with open(fileName, "a") as file:
      file.writelines(context + "\n")
if __name__ == '__main__':
  position=raw_input("请输入职位：")
  workPlace=raw_input("请输入工作地点：")
  z=zhiLian()
  z.spider(position,workPlace)

爬虫3

#encoding=utf-8
import urllib
import urllib2

import re


class teiba():
  def spider(self,name,startPage,endPage):
    url="http://tieba.baidu.com/f?ie=utf-8&"
    url+=urllib.urlencode({"kw":name})
    for page in range(startPage,endPage+1):
      pn=50*(page-1)
      urlFull=url+"&"+urllib.urlencode({"pn":pn})
      html=self.loadPage(url)
      self.dealPage(html,page)

  def loadPage(self,url):
    header={
      "User-Agent":" Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36"
    }
    request=urllib2.Request(url,headers=header)
    response=urllib2.urlopen(request)
    html=response.read()
    return html
  def dealPage(self,html,page):
    partten=re.compile(r'<a\s+rel="noreferrer"\s+href="/p/\d+" rel="external nofollow" \s+title=".*?"\s+target="_blank" class="j_th_tit\s+">(.*?)</a>',re.S)
    titleList=partten.findall(html)
    rstr=r'<span\s+class="topic-tag"\s+data-name=".*?">#(.*?)#</span>'
    for title in titleList:
      title=re.sub(rstr,"",title)
      self.writePage(title,page)
  def writePage(self,context,page):
    fileName="di"+str(page)+"yehtml.txt"
    with open(fileName,"a") as file:
      file.writelines(context+"\n")
if __name__ == '__main__':
  name=raw_input("请输入贴吧名：")
  startPage=raw_input("请输入起始页：")
  endPage=raw_input("请输入终止页：")
  t=teiba()
  t.spider(name,int(startPage),int(endPage))

我试试
爬取listid

def spyder_listid():
    headers= {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; Tablet PC 2.0; wbx 1.0.0; wbxapp 1.0.0; Zoom 3.6.0)"
    }
    response = requests.get('https://www.okooo.com/livecenter/football/',headers=headers)
    text = response.text.encode(response.encoding).decode(response.apparent_encoding)
    global listid
    listid = re.findall('match_detail_([0-9]*)',text)

爬取listeam

def spyder_listteam(id):
    headers= {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; Tablet PC 2.0; wbx 1.0.0; wbxapp 1.0.0; Zoom 3.6.0)"
    }
    response = requests.get('https://www.okooo.com/soccer/match/%s/ah/' % (id),headers=headers)
    text = response.text.encode(response.encoding).decode(response.apparent_encoding)
    listteam[id] = (re.findall(r'<div class="qpai_zi jsTeamName">(.*)</div>',text)[0],re.findall(r'<div class="qpai_zi_1 jsTeamName">(.*)</div>',text)[0])
    print(listteam[id])

根据id爬取listtime和listshui

def spyder_idpage(id):
    headers= {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; Tablet PC 2.0; wbx 1.0.0; wbxapp 1.0.0; Zoom 3.6.0)"
    }
    response = requests.get('https://www.okooo.com/soccer/match/%s/ah/ajax/?page=0&trnum=0&companytype=BaijiaBooks' % (id),headers=headers)
    # text = response.text.encode(response.encoding).decode(response.apparent_encoding)
    text = response.text
    resultlist = re.findall(r'<td class="feedbackObj"  title="开盘时间: 赛前([0-9]*)时([0-9]*)分"><a href="javascript:void\(0\);" class="nolink "><span attval="(.*)">(.*)</span></a></td>',text)
    listtime[id] = []
    listshui[id] = []
    for result in resultlist:
        listtime[id].append(result[0] + '时' + result[1] + '分')
        listshui[id].append(result[2])

整合版

import requests
import re
# import openpyxl
# import pandas as pd
# import os
# import pymysql
# import mysql.connector
# from bs4 import BeautifulSoup
# import pandas as pd
#取当日赛程ID到列表listid (元素中的match_detail_1176180（1176180为ID，只保留数字ID）)和主队队名到列表listteam()
#https://www.okooo.com/livecenter/football/
#将上面取到的赛程ID拼接到https://www.okooo.com/soccer/match/XXXXXX/ah/中的XXXXXX，再取这个地址的源码
#将源码中所有类似这样的<td class="feedbackObj" title="开盘时间: 赛前268时33分"><a href="javascript:void(0);" class="nolink "><span attval="受平手/半球">受平手/半球</span></a></td> 取出268时33分到列表listtime，取出“受平手/半球”到listshui。
#最终取到listid，listteam，listtime，listshui。再取系统时间到mydate
#将listid，mydate，listteam，listtime，listshui插入到数据库'zq'中对应的的id,date,name,time,shui即可。
 
# 连接数据库
#conn = mysql.connector.connect(
#    user='root',
#    password='qq438443820',
#    host='gz-cdb-k87y5qy1.sql.tencentcdb.com',
#    port='63938',
#    database='zq'
#)
# 创建游标
#cursor = conn.cursor()
# 遍历每一个列表并执行SQL语句
#query = "INSERT INTO zq (id,date, name, time, shui) VALUES (%s, %s, %s, %s, %s)"
#for val in zip(list3, list4, list1, list2):
#    cursor.execute("INSERT INTO zq (id,date, name, time, shui) VALUES (%s, %s, %s, %s, %s)", val)
#提交数据库
#conn.commit()
#关闭游标关闭连接
#cursor.close()
#conn.close()

listid = []
listtime = {}
listshui = {}
listteam = {}


def spyder_listid():
    headers= {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; Tablet PC 2.0; wbx 1.0.0; wbxapp 1.0.0; Zoom 3.6.0)"
    }
    response = requests.get('https://www.okooo.com/livecenter/football/',headers=headers)
    text = response.text.encode(response.encoding).decode(response.apparent_encoding)
    global listid
    listid = re.findall('match_detail_([0-9]*)',text)

def spyder_listteam(id):
    headers= {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; Tablet PC 2.0; wbx 1.0.0; wbxapp 1.0.0; Zoom 3.6.0)"
    }
    response = requests.get('https://www.okooo.com/soccer/match/%s/ah/' % (id),headers=headers)
    text = response.text.encode(response.encoding).decode(response.apparent_encoding)
    try:
        listteam[id] = (re.findall(r'<div class="qpai_zi jsTeamName">(.*)</div>',text)[0],re.findall(r'<div class="qpai_zi_1 jsTeamName">(.*)</div>',text)[0])
    except:
        return False
    return True

def spyder_idpage(id):
    headers= {
        "User-Agent": "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 10.0; WOW64; Trident/7.0; .NET4.0C; .NET4.0E; Tablet PC 2.0; wbx 1.0.0; wbxapp 1.0.0; Zoom 3.6.0)"
    }
    response = requests.get('https://www.okooo.com/soccer/match/%s/ah/ajax/?page=0&trnum=0&companytype=BaijiaBooks' % (id),headers=headers)
    text = response.text
    resultlist = re.findall(r'<td class="feedbackObj"  title="开盘时间: 赛前([0-9]*)时([0-9]*)分"><a href="javascript:void\(0\);" class="nolink "><span attval="(.*)">(.*)</span></a></td>',text)
    listtime[id] = []
    listshui[id] = []
    for result in resultlist:
        listtime[id].append(result[0] + '时' + result[1] + '分')
        listshui[id].append(result[2])

if __name__ == "__main__":
    spyder_listid()
    for id in listid:
        spyder_listteam(id)
        spyder_idpage(id)

你那网页好像进不去呀

现在有了吗?马上写

import requests
import re
from random import choice
import time

url = r'https://www.okooo.com/livecenter/football/'

usa = ['Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2228.0 Safari/537.36',
       'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.1 Safari/537.36', 
       'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36',
       'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2227.0 Safari/537.36',
       'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2226.0 Safari/537.36', 
       'Mozilla/5.0 (Windows NT 6.4; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36',
       'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2225.0 Safari/537.36',
       'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/41.0.2224.3 Safari/537.36', 
       'Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/40.0.2214.93 Safari/537.36', 
       'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2062.124 Safari/537.36', 
       'Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36',
       'Mozilla/5.0 (Windows NT 4.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/37.0.2049.0 Safari/537.36',
       'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36',
       'Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.67 Safari/537.36', 
       'Mozilla/5.0 (X11; OpenBSD i386) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1985.125 Safari/537.36',]
header = {'User-Agent': choice(usa),
          'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
          'Accept-Encoding': 'gzip, deflate, br',
          'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
          'Content-Type': 'application/x-javascript'}

response = requests.get(url, headers = header)
response.encoding = 'gbk'
content = response.text 

URL = 'https://www.okooo.com/soccer/match/{}/ah/'
result = re.findall(r'match_detail_(\d+).*?<a.*?"ctrl_homename jsJumpTo" reversion="0">(.*?)</a>.*?<a.*?"ctrl_awayname jsJumpTo" reversion="0">(.*?)</a>', content, re.DOTALL )
for ID, m, c in result:
    URL = URL.format(ID)
    curURL = URL + r'ajax/?page=0&trnum=0&companytype=BaijiaBooks'
    res = requests.get(curURL, headers = header)
    res.encoding = 'utf-8'
    con1 = res.text
    res2 = re.findall(r'<td class="feedbackObj"  title="(.*?)">.*?attval.*?>(.*?)</span></a></td>', con1, re.DOTALL)
    for j, k in res2:        
        print(f"ID:{ID} mainteam:{m} time:{j} shui:{k} curTime:{time.strftime('%Y年%m月%d日',time.localtime())}")

#encoding=utf-8
import urllib2
 
import re
 
 
class neihanba():
  def spider(self):
    fileName = "di" + str(page) + "yehtml.txt"
    with open(fileName, "a") as file:
      file.writelines(context + "\n")
if __name__ == '__main__':
  n=neihanba()
  n.spider()
 

py爬出数据注意点。