2020-04-21 09:15发布
import
requests
from
lxml
etree
def
getHTMLtext(url):
res
=
requests.get(url,timeout
30
)
# 处理中文编码问题
res.encoding
'gb2312'
# 转化html
html
etree.HTML(res.text)
# xpath提取tr标签下td的内容
HTMLtext
html.xpath(
"//tr/td/text()"
return
最多设置5个标签!
{var%20f='http://v.t.sina.com.cn/share/share.php?appkey=1515056452',u=z||d.location,p=['&url=',e(u),'&title=',e(t||d.title),'&source=',e(r),'&sourceUrl=',e(l),'&content=',c||'gb2312','&pic=',e(p||'')].join('');function%20a(){if(!window.open([f,p].join(''),'mb',['toolbar=0,status=0,resizable=1,width=440,height=430,left=',(s.width-440)/2,',top=',(s.height-430)/2].join('')))u.href=[f,p].join('');};if(/Firefox/.test(navigator.userAgent))setTimeout(a,0);else%20a();})(screen,document,encodeURIComponent,'','','/static/images/logo.png', '推荐 小冰块儿 的问题《python中如何将通过xpath提取部分html代码？》','http://www.shouhuola.com/answer/6832/131438.html','页面编码gb2312|utf-8默认gb2312'));){kind=link}
importrequestsfromlxmlimportetreedefgetHTMLtext(url):res=requests.get(url,timeout=30)# 处理中文编码问题res.encoding='gb2312'# 转化htmlhtml=etree.HTML(res.text)# xpath提取tr标签下td的内容HTMLtext=html.xpath("//tr/td/text()")returnHTMLtext一周热门 更多>