利用Python脚本生成sitemap.xml的实现方法
安装lxml
首先需要pipinstalllxml安装lxml库。
如果你在ubuntu上遇到了以下错误:
#include"libxml/xmlversion.h"
compilationterminated.
error:command'x86_64-linux-gnu-gcc'failedwithexitstatus1
----------------------------------------
Cleaningup...
Removingtemporarydir/tmp/pip_build_root...
Command/usr/bin/python-c"importsetuptools,tokenize;__file__='/tmp/pip_build_root/lxml/setup.py';exec(compile(getattr(tokenize,'open',open)(__file__).read().replace('\r\n','\n'),__file__,'exec'))"install--record/tmp/pip-O4cIn6-record/install-record.txt--single-version-externally-managed--compilefailedwitherrorcode1in/tmp/pip_build_root/lxml
Exceptioninformation:
Traceback(mostrecentcalllast):
File"/usr/lib/python2.7/dist-packages/pip/basecommand.py",line122,inmain
status=self.run(options,args)
File"/usr/lib/python2.7/dist-packages/pip/commands/install.py",line283,inrun
requirement_set.install(install_options,global_options,root=options.root_path)
File"/usr/lib/python2.7/dist-packages/pip/req.py",line1435,ininstall
requirement.install(install_options,global_options,*args,**kwargs)
File"/usr/lib/python2.7/dist-packages/pip/req.py",line706,ininstall
cwd=self.source_dir,filter_stdout=self._filter_install,show_stdout=False)
File"/usr/lib/python2.7/dist-packages/pip/util.py",line697,incall_subprocess
%(command_desc,proc.returncode,cwd))
InstallationError:Command/usr/bin/python-c"importsetuptools,tokenize;__file__='/tmp/pip_build_root/lxml/setup.py';exec(compile(getattr(tokenize,'open',open)(__file__).read().replace('\r\n','\n'),__file__,'exec'))"install--record/tmp/pip-O4cIn6-record/install-record.txt--single-version-externally-managed--compilefailedwitherrorcode1in/tmp/pip_build_root/lxml
请安装以下依赖：
sudoapt-getinstalllibxml2-devlibxslt1-dev
Python代码
下面是生成sitemap和sitemapindex索引的代码，可以按照需求传入需要的参数，或者增加字段：
#!/usr/bin/envpython
#-*-coding:utf-8-*-
importio
importre
fromlxmlimportetree
defgenerate_xml(filename,url_list):
"""Generateanewxmlfileuseurl_list"""
root=etree.Element('urlset',
xmlns="http://www.sitemaps.org/schemas/sitemap/0.9")
foreachinurl_list:
url=etree.Element('url')
loc=etree.Element('loc')
loc.text=each
url.append(loc)
root.append(url)
header=u'<?xmlversion="1.0"encoding="UTF-8"?>\n'
s=etree.tostring(root,encoding='utf-8',pretty_print=True)
withio.open(filename,'w',encoding='utf-8')asf:
f.write(unicode(header+s))
defupdate_xml(filename,url_list):
"""Addnewurl_listtooriginxmlfile."""
f=open(filename,'r')
lines=[i.strip()foriinf.readlines()]
f.close()
old_url_list=[]
foreach_lineinlines:
d=re.findall('<loc>(http:\/\/.+)<\/loc>',each_line)
old_url_list+=d
url_list+=old_url_list
generate_xml(filename,url_list)
defgeneratr_xml_index(filename,sitemap_list,lastmod_list):
"""Generatesitemapindexxmlfile."""
root=etree.Element('sitemapindex',
xmlns="http://www.sitemaps.org/schemas/sitemap/0.9")
foreach_sitemap,each_lastmodinzip(sitemap_list,lastmod_list):
sitemap=etree.Element('sitemap')
loc=etree.Element('loc')
loc.text=each_sitemap
lastmod=etree.Element('lastmod')
lastmod.text=each_lastmod
sitemap.append(loc)
sitemap.append(lastmod)
root.append(sitemap)
header=u'<?xmlversion="1.0"encoding="UTF-8"?>\n'
s=etree.tostring(root,encoding='utf-8',pretty_print=True)
withio.open(filename,'w',encoding='utf-8')asf:
f.write(unicode(header+s))
if__name__=='__main__':
urls=['http://www.baidu.com']*10
mods=['2004-10-01T18:23:17+00:00']*10
generatr_xml_index('index.xml',urls,mods)
效果
生成的效果应该是这种格式：
sitemap格式:
<?xmlversion="1.0"encoding="UTF-8"?> <urlsetxmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> <url> <loc>http://www.example.com/foo.html</loc> </url> </urlset>
sitemapindex格式：
<?xmlversion="1.0"encoding="UTF-8"?> <sitemapindexxmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> <sitemap> <loc>http://www.example.com/sitemap1.xml.gz</loc> <lastmod>2004-10-01T18:23:17+00:00</lastmod> </sitemap> <sitemap> <loc>http://www.example.com/sitemap2.xml.gz</loc> <lastmod>2005-01-01</lastmod> </sitemap> </sitemapindex>
lastmod时间格式的问题
格式是用ISO8601的标准，如果是linux/unix系统，可以使用以下函数获取
defget_lastmod_time(filename):
time_stamp=os.path.getmtime(filename)
t=time.localtime(time_stamp)
#returntime.strftime('%Y-%m-%dT%H:%M:%S+08:00',t)
returntime.strftime('%Y-%m-%dT%H:%M:%SZ',t)
优化
一般来说，用lxml效率低并且内存占用比较大，可以直接用文件的write方法创建。
defgenerate_xml(filename,url_list):
withgzip.open(filename,"w")asf:
f.write("""<?xmlversion="1.0"encoding="utf-8"?>
<urlsetxmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n""")
foriinurl_list:
f.write("""<url><loc>%s</loc></url>\n"""%i)
f.write("""</urlset>""")
defappend_xml(filename,url_list):
withgzip.open(filename,'r')asf:
foreach_lineinf:
d=re.findall('<loc>(http:\/\/.+)<\/loc>',each_line)
url_list.extend(d)
generate_xml(filename,set(url_list))
defmodify_time(filename):
time_stamp=os.path.getmtime(filename)
t=time.localtime(time_stamp)
returntime.strftime('%Y-%m-%dT%H:%M:%S:%SZ',t)
defnew_xml(filename,url_list):
generate_xml(filename,url_list)
root=dirname(filename)
withopen(join(dirname(root),"sitemap.xml"),"w")asf:
f.write('<?xmlversion="1.0"encoding="utf-8"?>\n<sitemapindexxmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n')
foriinglob.glob(join(root,"*.xml.gz")):
lastmod=modify_time(i)
i=i[len(CONFIG.SITEMAP_PATH):]
f.write("<sitemap>\n<loc>http:/%s</loc>\n"%i)
f.write("<lastmod>%s</lastmod>\n</sitemap>\n"%lastmod)
f.write('</sitemapindex>')
总结
以上就是这篇文章的全部内容了，希望本文的内容对大家学习或者使用python能带来一定的帮助，如果有疑问大家可以留言交流。谢谢大家对毛票票的支持。