dfcf_spider

dfcf_spider

实验源代码:

# 目标采集：帖子标题，阅读数、评论数、链接、发布时间
import requests
from bs4 import BeautifulSoup
import time
import csv
import re
#复制请求头
# 在请求网页爬取的时候，输出的text信息中会出现抱歉，无法访问等字眼，这就是禁止爬取，需要通过反爬机制去解决这个问题。
# headers是解决requests请求反爬的方法之一，相当于我们进去这个网页的服务器本身，假装自己本身在爬取数据。
# 对反爬虫网页，可以设置一些headers信息，模拟成浏览器取访问网站 。
head ={'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
'Accept-Encoding':'gzip,deflate',
'Accept-Language':'zh-CN,zh;q=0.9',
'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Cookie':'st_pvi=87732908203428;st_si=12536249509085;qgqp_b_id=9777e9c5e51986508024bda7f12e6544;_adsame_fullscreen_16884=1',
'Host':'guba.eastmoney.com',
'Referer':'http://guba.eastmoney.com/list,600596,f_1.html',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0(WindowsNT6.1;Win64;x64)AppleWebKit/537.36(KHTML,likeGecko)Chrome/65.0.3325.181Safari/537.36'}
 
#设置数据存储方式，csv表格写入
f = open('dfcw.csv','a',newline='')
w = csv.writer(f)
 
#获取帖子详细时间，列表也没有年份，可以作为获取帖子其他详细内容的通用方法
def get_time(url):
    try:
        q = requests.get(url,headers=head)
        soup = BeautifulSoup(q.text,'html.parser')
        ptime = soup.find('div',{'class':'zwfbtime'}).get_text()
        ptime = re.findall(r'd{4}-d{2}-d{2} d{2}:d{2}:d{2}',ptime)[0]
        print(ptime)
        return ptime
    except:
        return ''
 
#获取列表页第n页的具体目标信息，由BeautifulSoup解析完成
def get_urls(url):
    print("url:"+url)
    baseurl = 'http://guba.eastmoney.com/'
    q = requests.get(url,headers=head)
    soup = BeautifulSoup(q.text,'html.parser')
    urllist = soup.findAll('div',{'class':'articleh'})
    # print(urllist)
    for i in urllist:
        if i.find('a') != None:
            try:
                detailurl = i.find('a').attrs['href'].replace('/','')
                # 找到详情页地址
                # print("ddd"+detailurl)
                titel = i.find('a').get_text()
                yuedu = i.find('span',{'class':'l1'}).get_text()
                pinlun = i.find('span', {'class': 'l2'}).get_text()
                #获取帖子时间
                ptime = get_time(baseurl+detailurl)
                w.writerow([detailurl,titel,yuedu,pinlun,ptime])
                # print("zz"+baseurl + detailurl)
            except:
                pass
#循环所有页数
for i in range(1,2):
    print(i)
    #新安股份吧第1~2页，这里可以改到第N页
    get_urls('http://guba.eastmoney.com/list,600596,f_'+str(i)+'.html')

实验结果截图: