#coding:utf-8
import requests
import urllib2
import urllib
```
from lxml import etree
class Tieba:
  def __init__(self):
    self.tiebaName = raw_input("請(qǐng)輸入需要爬取的貼吧:")
    self.beginPage = int(raw_input("請(qǐng)輸入爬取的起始頁(yè)："))
    self.endPage = int(raw_input("請(qǐng)輸入爬取的結(jié)束頁(yè)："))
    self.baseURL = "http://tieba.baidu.com"
    #self.headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/59.0.3071.86 Safari/537.36"}
    self.headers = {"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1 Trident/5.0;"} def startWork(self):
    """
      發(fā)送貼吧每一頁(yè)的url請(qǐng)求
    """
    for page in range(self.beginPage, self.endPage + 1):
      pn = (page - 1) * 50
      keyword = {"kw" : self.tiebaName, "pn" : pn}
      kw = urllib.urlencode(keyword)
      url = self.baseURL + "/f?" + kw
      #print url
      html = self.loadRequest(url)
      self.loadPage(html)
  def loadRequest(self, url):
    """
      發(fā)送請(qǐng)求，返回響應(yīng)
      url: 發(fā)送請(qǐng)求的url地址
    """
    request = urllib2.Request(url, headers = self.headers)
    #request = urllib2.Request(url)
    response = urllib2.urlopen(request)
    return response.read()
  def loadPage(self, html):
    """
      提取每個(gè)帖子的url，并發(fā)送請(qǐng)求，獲取響應(yīng)
      html: 貼吧每一頁(yè)的html
    """
    content = etree.HTML(html)
    print '------'
    print content
    # xpath 返回的所有匹配成功后的結(jié)果的列表
    #pagelink_list = content.xpath("http://div[@class='threadlist_lz clearfix']/div/a[@class='j_th_tit']/@href")
    pagelink_list = content.xpath("http://div[@class='col2_right j_threadlist_li_right']//div/a/@href")
    pagelink_list = content.xpath("http://div[@class='t_con cleafix']//div/a/@href")
    for link in pagelink_list:
      print link
      self.loadImage(self.loadRequest(self.baseURL + link))
  def loadImage(self, html):
    """
      提取帖子里用戶(hù)發(fā)送的圖片的url地址
      html: 每個(gè)帖子的html
    """
    content = etree.HTML(html)
    imagelink_list = content.xpath("http://div[@class='p_content ']//img[@class='BDE_Image']/@src")
    for link in imagelink_list:
      self.writeImage(self.loadRequest(link), link[-10:])
  def writeImage(self, data, filename):
    """
      將圖片的響應(yīng)數(shù)據(jù)，寫(xiě)入到本地磁盤(pán)里
      data: 圖片的響應(yīng)數(shù)據(jù)
      filename: 文件名(圖片url的后10位)
    """
    print "正在保存圖片...%s" % filename
    with open(filename, "wb") as f:
      f.write(data)
if __name__ == "__main__":
  tieba = Tieba()
  tieba.startWork()