# -*- coding:utf-8 -*-

import urllib
import urllib2
from lxml import etree


def loadPage(url):
 """
  作用：根據(jù)url發(fā)送請(qǐng)求，獲取服務(wù)器響應(yīng)文件
  url: 需要爬取的url地址
 """
 #print url
 #美女
 # headers = {"User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"}

 request = urllib2.Request(url)
 html = urllib2.urlopen(request).read()
 # 解析HTML文檔為HTML DOM模型
 content = etree.HTML(html)
 #print content
 # 返回所有匹配成功的列表集合
 link_list = content.xpath('//div[@class="t_con cleafix"]/div/div/div/a/@href')

 #link_list = content.xpath('//a[@class="j_th_tit"]/@href')
 for link in link_list:
  fulllink = "http://tieba.baidu.com" + link
  # 組合為每個(gè)帖子的鏈接
  #print link
  loadImage(fulllink)


# 取出每個(gè)帖子里的每個(gè)圖片連接
def loadImage(link):
 headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
 request = urllib2.Request(link, headers = headers)
 html = urllib2.urlopen(request).read()
 # 解析
 content = etree.HTML(html)
 # 取出帖子里每層層主發(fā)送的圖片連接集合
 #link_list = content.xpath('//img[@class="BDE_Image"]/@src')
 #link_list = content.xpath('//div[@class="post_bubble_middle"]')
 link_list = content.xpath('//img[@class="BDE_Image"]/@src')
 # 取出每個(gè)圖片的連接
 for link in link_list:
  print link
  writeImage(link)


def writeImage(link):
 """
  作用：將html內(nèi)容寫(xiě)入到本地
  link：圖片連接
 """
 #print "正在保存 " + filename
 headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
 # 文件寫(xiě)入
 request = urllib2.Request(link, headers = headers)
 # 圖片原始數(shù)據(jù)
 image = urllib2.urlopen(request).read()
 # 取出連接后10位做為文件名
 filename = link[-10:]
 # 寫(xiě)入到本地磁盤(pán)文件內(nèi)
 with open("d:\image\\"+filename, "wb") as f:
  f.write(image)
 print "已經(jīng)成功下載 "+ filename

def tiebaSpider(url, beginPage, endPage):
 """
  作用：貼吧爬蟲(chóng)調(diào)度器，負(fù)責(zé)組合處理每個(gè)頁(yè)面的url
  url : 貼吧url的前部分
  beginPage : 起始頁(yè)
  endPage : 結(jié)束頁(yè)
 """
 for page in range(beginPage, endPage + 1):
  pn = (page - 1) * 50
  filename = "第" + str(page) + "頁(yè).html"
  fullurl = url + "&pn=" + str(pn)
  print fullurl
  loadPage(fullurl)
  #print html

  print "謝謝使用"

if __name__ == "__main__":
 kw = raw_input("請(qǐng)輸入需要爬取的貼吧名:")
 beginPage = int(raw_input("請(qǐng)輸入起始頁(yè)："))
 endPage = int(raw_input("請(qǐng)輸入結(jié)束頁(yè)："))

 url = "http://tieba.baidu.com/f?"
 key = urllib.urlencode({"kw": kw})
 fullurl = url + key
 tiebaSpider(fullurl, beginPage, endPage)