安装lxml
首先需要pip install lxml
安装lxml库。
如果你在ubuntu上遇到了以下错误:
#include "libxml/xmlversion.h" compilation terminated. error: command 'x86_64-linux-gnu-gcc' failed with exit status 1 ---------------------------------------- Cleaning up... Removing temporary dir /tmp/pip_build_root... Command /usr/bin/python -c "import setuptools, 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 --compile failed with error code 1 in /tmp/pip_build_root/lxml Exception information: Traceback (most recent call last): File "/usr/lib/python2.7/dist-packages/pip/basecommand.py", line 122, in main status = self.run(options, args) File "/usr/lib/python2.7/dist-packages/pip/commands/install.py", line 283, in run requirement_set.install(install_options, global_options, root=options.root_path) File "/usr/lib/python2.7/dist-packages/pip/req.py", line 1435, in install requirement.install(install_options, global_options, *args, **kwargs) File "/usr/lib/python2.7/dist-packages/pip/req.py", line 706, in install cwd=self.source_dir, filter_stdout=self._filter_install, show_stdout=False) File "/usr/lib/python2.7/dist-packages/pip/util.py", line 697, in call_subprocess % (command_desc, proc.returncode, cwd)) InstallationError: Command /usr/bin/python -c "import setuptools, 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 --compile failed with error code 1 in /tmp/pip_build_root/lxml
请安装以下依赖:
sudo apt-get install libxml2-dev libxslt1-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/env python # -*- coding:utf-8 -*- import io import re from lxml import etree def generate_xml(filename, url_list): """Generate a new xml file use url_list""" root = etree.Element('urlset', xmlns="http://www.sitemaps.org/schemas/sitemap/0.9") for each in url_list: url = etree.Element('url') loc = etree.Element('loc') loc.text = each url.append(loc) root.append(url) header = u'<"1.0" encoding="UTF-8"?>\n' s = etree.tostring(root, encoding='utf-8', pretty_print=True) with io.open(filename, 'w', encoding='utf-8') as f: f.write(unicode(header+s)) def update_xml(filename, url_list): """Add new url_list to origin xml file.""" f = open(filename, 'r') lines = [i.strip() for i in f.readlines()] f.close() old_url_list = [] for each_line in lines: d = re.findall('<loc>(http:\/\/.+)<\/loc>', each_line) old_url_list += d url_list += old_url_list generate_xml(filename, url_list) def generatr_xml_index(filename, sitemap_list, lastmod_list): """Generate sitemap index xml file.""" root = etree.Element('sitemapindex', xmlns="http://www.sitemaps.org/schemas/sitemap/0.9") for each_sitemap, each_lastmod in zip(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'<"1.0" encoding="UTF-8"?>\n' s = etree.tostring(root, encoding='utf-8', pretty_print=True) with io.open(filename, 'w', encoding='utf-8') as f: 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:
<"1.0" encoding="UTF-8"?> <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9"> <url> <loc>http://www.example.com/foo.html</loc> </url> </urlset>
sitemapindex格式:
<"1.0" encoding="UTF-8"?> <sitemapindex xmlns="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ISO 8601的标准,如果是linux/unix系统,可以使用以下函数获取
def get_lastmod_time(filename): time_stamp = os.path.getmtime(filename) t = time.localtime(time_stamp) # return time.strftime('%Y-%m-%dT%H:%M:%S+08:00', t) return time.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。
def generate_xml(filename, url_list): with gzip.open(filename,"w") as f: f.write("""<"1.0" encoding="utf-8"?> <urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n""") for i in url_list: f.write("""<url><loc>%s</loc></url>\n"""%i) f.write("""</urlset>""") def append_xml(filename, url_list): with gzip.open(filename, 'r') as f: for each_line in f: d = re.findall('<loc>(http:\/\/.+)<\/loc>', each_line) url_list.extend(d) generate_xml(filename, set(url_list)) def modify_time(filename): time_stamp = os.path.getmtime(filename) t = time.localtime(time_stamp) return time.strftime('%Y-%m-%dT%H:%M:%S:%SZ', t) def new_xml(filename, url_list): generate_xml(filename, url_list) root = dirname(filename) with open(join(dirname(root), "sitemap.xml"),"w") as f: f.write('<"1.0" encoding="utf-8"?>\n<sitemapindex xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n') for i in glob.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。谢谢大家对的支持。
免责声明:本站文章均来自网站采集或用户投稿,网站不提供任何软件下载或自行开发的软件! 如有用户或公司发现本站内容信息存在侵权行为,请邮件告知! 858582#qq.com
《魔兽世界》大逃杀!60人新游玩模式《强袭风暴》3月21日上线
暴雪近日发布了《魔兽世界》10.2.6 更新内容,新游玩模式《强袭风暴》即将于3月21 日在亚服上线,届时玩家将前往阿拉希高地展开一场 60 人大逃杀对战。
艾泽拉斯的冒险者已经征服了艾泽拉斯的大地及遥远的彼岸。他们在对抗世界上最致命的敌人时展现出过人的手腕,并且成功阻止终结宇宙等级的威胁。当他们在为即将于《魔兽世界》资料片《地心之战》中来袭的萨拉塔斯势力做战斗准备时,他们还需要在熟悉的阿拉希高地面对一个全新的敌人──那就是彼此。在《巨龙崛起》10.2.6 更新的《强袭风暴》中,玩家将会进入一个全新的海盗主题大逃杀式限时活动,其中包含极高的风险和史诗级的奖励。
《强袭风暴》不是普通的战场,作为一个独立于主游戏之外的活动,玩家可以用大逃杀的风格来体验《魔兽世界》,不分职业、不分装备(除了你在赛局中捡到的),光是技巧和战略的强弱之分就能决定出谁才是能坚持到最后的赢家。本次活动将会开放单人和双人模式,玩家在加入海盗主题的预赛大厅区域前,可以从强袭风暴角色画面新增好友。游玩游戏将可以累计名望轨迹,《巨龙崛起》和《魔兽世界:巫妖王之怒 经典版》的玩家都可以获得奖励。