爬取uputoo视频

爬取uputoo视频

import json
import urllib.request
import os,time
from math import ceil
from lxml import etree
import re

import random
def get_heders():
	ua_list = [
		"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0",
		"Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10",
		"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.57.2 (KHTML, like Gecko) Version/5.1.7 Safari/534.57.2",
		"Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133 Safari/534.16",
		"Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 SE 2.X MetaSr 1.0",


	]
	#随机抽取
	import random
	ua = random.choice(ua_list)
	headers = {
		'User-Agent':ua,
	}
	return headers


def handle_request(url,page):
	url = url.format(page)
	headers = get_heders()
	request = urllib.request.Request(url=url,headers=headers)
	return request
def parse_resp(response):
	tree = etree.HTML(response)
	href_list = tree.xpath('//div[@class="mask"]/a/@href')
	return href_list

def main():
	dirname = "video"
	url = "http://wallpaper.upupoo.com/store/browVi/1-0-0-{}.htm"
	for page in range(3,10):
		print("正在下载%s" % page)
		request = handle_request(url,page)
		response = urllib.request.urlopen(request).read().decode('utf-8')
		href_list = parse_resp(response)
		for hrefnot in href_list:
			href = "http://wallpaper.upupoo.com/" + hrefnot
			headers = get_heders()
			request = urllib.request.Request(url=href,headers=headers)
			content = urllib.request.urlopen(request).read().decode('utf-8')
			pat = re.compile('.*?var video = loadVideo.(.*?.mp4).*')
			ret = pat.findall(content)[0].strip("'")
			
			filename = dirname + ret.split('/')[-1]
			try:
				urllib.request.urlretrieve(ret,filename)
				time.sleep(1)
				print("结束%s" % page)
			except Exception as e:
				print('继续吓一跳')
			

		
		


















if __name__ == '__main__':
	main()