【源码分享】结合爬虫用可实现自动更新地图,后期会更新爬虫源码
import time
date = time.strftime('%Y-%m-%d', time.localtime())
list = [url.strip() for url in open('C:\\Users\\Administ\URL推送.txt').readlines()]
#需要自己创建一个urllist文本
class sitemaps:
def __init__(self):
self.n = 1
#指定xml文件的路径位置
def name(self, c):
opxml = open('C:\\Users\\Administrator\\Desktop\\sitemap%s.xml' % c, 'a')
opxml.write('''<?xml version="1.0" encoding="utf-8"?>
<urlset>\n''')
return opxml
def zhizuo(self, urllist):
xmldata = self.name(self.n)
# print '''<?xml version="1.0" encoding="utf-8"?>
# <urlset>'''
m = 0
for i in urllist:
i = i.strip()
m += 1
sitemaps = ''' <url>
<loc>''' + str(i) + '''</loc>
<lastmod>''' + date + '''</lastmod>
<changefreq>daily</changefreq>
<priority>0.8</priority>
</url>\n'''
xmldata.write(sitemaps)
# print sitemaps
if m == 50000:
self.n += 1
xmldata.write('</urlset>\n')
xmldata = self.name(self.n)
m = 0
else:
pass
xmldata.write('</urlset>\n')
print('网站地图自动生成--成功啦')
if __name__ == '__main__':
p = sitemaps()
p.zhizuo(list)