python爬蟲爬取幽默笑話網(wǎng)站

res=requests.get(url,headers=headers)
html = res.text
 
lxml 獲取節(jié)點(diǎn)寫法
element=etree.HTML(html)
divEle=element.xpath("http://div[@class='article-text']")[0]  # 獲取div節(jié)點(diǎn)
div= etree.tostring(divEle, encoding = 'utf-8' ).decode('utf-8') # 轉(zhuǎn)換為div字符串

# 第一種方式：replace
content = re.findall('<div class="article-text">(.*?)</div>',html,re.S)
content = content[0].replace('\r','').replace('\t','').replace('<p>','').replace('</p>','').strip()

# 第二種方式：sub
for index in range(len(content)):
  content[index] = re.sub(r'(\r|\t|<p>|<\/p>)+','',content[index]).strip()
 
list = ''.join(content)
print(list)

import requests
import threadpool
import time
import os,sys
import re
from lxml import etree
from lxml.html import tostring
 
 
class ScrapDemo():
  next_page_url=""  #下一頁的URL
  page_num=1 #當(dāng)前頁
  detail_url_list=0 #詳情頁面URL地址list
  deepth=0 #設(shè)置抓取的深度
  headers = {
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.84 Safari/537.36"
  }
  fileNum=0
 
  def __init__(self,url):
    self.scrapyIndex(url)
 
  def threadIndex(self,urllist): #開啟線程池
    if len(urllist) == 0:
      print("請(qǐng)輸入需要爬取的地址")
      return False
    ScrapDemo.detail_url_list=len(urllist)
    pool=threadpool.ThreadPool(len(urllist))
    requests=threadpool.makeRequests(self.detailScray,urllist)
    for req in requests:  
      pool.putRequest(req)
      time.sleep(0.5)
    pool.wait()
 
  def detailScray(self,url): # 獲取html結(jié)構(gòu)
    if not url == "":
      url='http://xiaohua.zol.com.cn/{}'.format(url)
      res=requests.get(url,headers=ScrapDemo.headers)
      html=res.text
      # element=etree.HTML(html)
      # divEle=element.xpath("http://div[@class='article-text']")[0]  # Element div     
      self.downloadText(html) 
 
  def downloadText(self,ele): # 抓取數(shù)據(jù)并存為txt文件
    clist = re.findall('<div class="article-text">(.*?)</div>',ele,re.S)
    for index in range(len(clist)):
      '''
        正則表達(dá)式：過濾掉回車、制表符和p標(biāo)簽
      '''
      clist[index]=re.sub(r'(\r|\t|<p>|<\/p>)+','',clist[index]) 
    content="".join(clist)
    # print(content) 
    basedir=os.path.dirname(__file__)
    filePath=os.path.join(basedir)
    filename="xiaohua{0}-{1}.txt".format(ScrapDemo.deepth,str(ScrapDemo.fileNum))
    file=os.path.join(filePath,'file_txt',filename)
    try:
      f=open(file,"w")
      f.write(content)
      if ScrapDemo.fileNum == (ScrapDemo.detail_url_list - 1):
        print(ScrapDemo.next_page_url)
        print(ScrapDemo.deepth)
        if not ScrapDemo.next_page_url == "":
          self.scrapyIndex(ScrapDemo.next_page_url)
    except Exception as e:
      print("Error:%s" % str(e))
 
    ScrapDemo.fileNum=ScrapDemo.fileNum+1
    print(ScrapDemo.fileNum)
 
  def scrapyIndex(self,url): 
    if not url == "":
      ScrapDemo.fileNum=0
      ScrapDemo.deepth=ScrapDemo.deepth+1
      print("開啟第{0}頁抓取".format(ScrapDemo.page_num))
      res=requests.get(url,headers=ScrapDemo.headers)
      html=res.text
      element=etree.HTML(html)
      a_urllist=element.xpath("http://a[@class='all-read']/@href") # 當(dāng)前頁所有查看全文
      next_page=element.xpath("http://a[@class='page-next']/@href") # 獲取下一頁的url
      ScrapDemo.next_page_url='http://xiaohua.zol.com.cn/{}'.format(next_page[0])
      if not len(next_page) == 0 and ScrapDemo.next_page_url != url:
        ScrapDemo.page_num=ScrapDemo.page_num+1
        self.threadIndex(a_urllist[:]) 
      else:
        print('下載完成，當(dāng)前頁數(shù)為{}頁'.format(ScrapDemo.page_num))
        sys.exit()

from app import ScrapDemo
url="http://xiaohua.zol.com.cn/youmo/"
ScrapDemo(url)