# coding:utf-8
# 爬取百度贴吧.py

import urllib.request
import urllib
urllib2 = urllib.request

def loadPage(url,filename):
	"""
	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
	filename：处理的文件名
	"""
	print("正在下载"+filename)
	headers ={"User-Agent":
	"Mozilla/5.0 (Windows NT 6.1;) Apple....\
	Mozilla/5.0 (X11; Cros i686 2268.111.0)...\
	Mozilla/5.0 (Macintosh; U; PPC Mac OS X)...\
	Mozilla/5.0 (Macintosh;Intel Mac OS)..."
	}

	request = urllib2.Request(url,headers=headers)
	response = urllib2.urlopen(request)
	html = response.read()
	return html
	# return html.decode('utf-8')
def writePage(html,filename):
	"""
	作用：将html内容写入到本地
	html：服务器响应文件内容
	"""
	print("正在保存"+filename)

	# 文件写入，这样写无需写close(),需要编码转换
	with open(filename,"w+",encoding='utf-8') as f:
		f.write(html.decode("utf-8"))
	
	print('-'*30)

def tiebaSpider(url,beginPage,endPage,kw):

	"""
	贴吧爬虫调度器，负责组合处理每个页面的url地址
	url:贴吧url的前半部分
	beginPage:起始页
	endPage：结束页
	"""
	for page in range(beginPage,endPage+1):
		pn = (page-1)*50
		filename = str(kw)+"贴吧第" + str(page) + "页.html"
		fullurl = url + "&pn=" + str(pn)
		# print(fullurl)
		html = loadPage(fullurl,filename)
		# print(html)
		writePage(html,filename)
	print("已完成，谢谢使用！")

if __name__ == "__main__":
	kw = input("请输入需要爬取贴吧名字：")
	while True:
		try:
			beginPage = int(input("请输入要抓取'%s'贴吧的开始页数："%kw))
			endPage = int(input("请输入要抓取'%s'贴吧的结束页数："%kw))
			if int(endPage)>= int(beginPage):
				url = "http://tieba.baidu.com/f?"
				key = urllib.parse.urlencode({"kw":kw})
				fullurl = url + key
				tiebaSpider(fullurl, beginPage,endPage,kw)
				break
			else:
				print("请输入正确的页数,并且结束页数要大于等于开始页数")
		except:
			print("请输入正确的页数！")