Python爬虫-爬取贴吧中每个帖子内的楼主图片

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

import urllib.request
from lxml import etree


def loadPage(url):
	"""
	 作用：根据url发送请求，获取服务器响应文件
	 url: 需要爬取的url地址
	"""
	# 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 = urllib.request.Request(url)
	html = urllib.request.urlopen(request).read()
	# 解析HTML文档为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
		# 组合为每个帖子的链接
		# print link
		loadImage(fulllink)


# 取出每个帖子里的每个图片连接
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 = urllib.request.Request(link, headers=headers)
	html = urllib.request.urlopen(request).read()
	# 解析
	content = etree.HTML(html)
	# 取出帖子里每层层主发送的图片连接集合
	# 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')
	# 取出每个图片的连接
	for link in link_list:
		print("link:" + link)
		writeImage(link)


def writeImage(link):
	"""
	 作用：将html内容写入到本地
	 link：图片连接
	"""
	# 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"}
	# 文件写入
	request = urllib.request.Request(link, headers=headers)
	# 图片原始数据
	image = urllib.request.urlopen(request).read()
	# 取出连接后10位做为文件名
	filename = link[-10:]
	# 写入到本地磁盘文件内
	with open("/Users/didi/Downloads/crawlertest/" + filename, "wb") as f:
		f.write(image)
	# print("已经成功下载 " + filename)


def tiebaSpider(url, beginPage, endPage):
	"""
	 作用：贴吧爬虫调度器，负责组合处理每个页面的url
	 url : 贴吧url的前部分
	 beginPage : 起始页
	 endPage : 结束页
	"""
	for page in range(beginPage, endPage + 1):
		pn = (page - 1) * 50
		filename = "第" + str(page) + "页.html"
		print(filename)
		fullurl = url + "&pn=" + str(pn)
		print(fullurl)
		loadPage(fullurl)
		# print html
		
		print("下载完成")


if __name__ == "__main__":
	kw = input("请输入需要爬取的贴吧名:")
	beginPage = int(input("请输入起始页："))
	endPage = int(input("请输入结束页："))
	
	url = "http://tieba.baidu.com/f?"
	key = urllib.parse.urlencode({"kw": kw})
	fullurl = url + key
	tiebaSpider(fullurl, beginPage, endPage)