<爬虫>黑板爬虫闯关01

转载于 2019-03-10 19:24:00 发布 · 58 阅读

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/shuimohei/p/10506561.html

文章标签：

import requests
from lxml import etree
import time
'''
	黑板爬虫闯关
	网址:http://www.heibanke.com/lesson/crawler_ex00/
'''
start_time = time.time()
start_url = "http://www.heibanke.com/lesson/crawler_ex00/"
res = requests.get(start_url)
res.encoding = "utf8"
html = etree.HTML(res.content)
Num = html.xpath("//h3/text()")[0][-5:]
print(Num)
while Num:
	url = "http://www.heibanke.com/lesson/crawler_ex00/" + str(Num) + "/"
	print(url)
	res = requests.get(url)
	res.encoding = "utf8"
	html = etree.HTML(res.content)
	Num = html.xpath("//h3/text()")[0]
	N = []
	for i in Num:
		if i.isdigit() == True:
			N.append(i)
	Num = "".join(N)
	print(Num)
end_time = time.time()
print(end_time-start_time)

转载于:https://www.cnblogs.com/shuimohei/p/10506561.html