通过之前的学习，我们编写了两个基本的爬虫。但对于一些内容大的网站，我们就需要对其进行跟踪链接，利用正则表达式来确定需要下载的页面。
1.正则表达式 下载链接 ，其中 urlparse 模块用来实现相对路径转换成绝对路径，通过一个
import re
import urlparse
def link_crawler(seed_url, link_regex):
"""Crawl from the given seed URL following links matched by link_regex
"""
crawl_queue = [seed_url] # the queue of URL's to download
while crawl_queue:
url = crawl_queue.pop()
html = download(url)
# filter for links matching our regular expression
for link in get_links(html):
if re.match(link_regex, link):
# add this link to the crawl queue
crawl_queue.append(link)
def get_links(html):
"""Return a list of links from html
"""
# a regular expression to extract all links from the webpage
webpage_regex = re.compile('<a[^>]+href=["\'](.*?)["\']', re.IGNORECASE)
# list of all links from the webpage
return webpage_regex.findall(html)
if __name__ == '__main__':
link_crawler('http://example.webscraping.com', '/(index|view)')
