标签:sina tracking count print com requests nbsp mysq attrs
range=all&c=news&q=%BD%F0%D0%E3%CF%CD&from=home").text #网址
soup=BeautifulSoup(‘‘.join(html))
a=soup(‘div‘,{ ‘class‘ : ‘l_v2‘ })
race=[]
c=""
race=str(a).split("新闻")[1].split("篇")[0].split(",") #获取网址有多少页码
b=len(race)
for i in range(b):
c+=race[i]
b=string.atoi(c)/20
return b
def getContents(html):#获取指定新闻内容
soup=BeautifulSoup(‘‘.join(html))
rs=re.compile("fgray_time")
html=soup.findAll(‘span‘,attrs={‘class‘:rs})
rs=re.compile("box-result clearfix")
contents=soup.findAll(‘div‘,attrs={‘class‘:rs})
for c in html:
length=len(c.text.split(‘ ‘))
if length==3:
source=c.text.split(‘ ‘)[0]#新闻来源
time=c.text.split(‘ ‘)[1]+‘ ‘+c.text.split(‘ ‘)[2]#新闻发表时间
print source
print time
else:
time=c.text#新闻发表时间
source=‘‘#新闻来源
print time
for i in contents:
title= i.h2.a.text#新闻标题
content= i.p.text#新闻简单介绍内容
## print html
if __name__=="__main__":
count=getPage()
print 111
for i in range(count):
print getContents(getHtml(i))
print 222
标签:sina tracking count print com requests nbsp mysq attrs
原文地址:http://www.cnblogs.com/cxchanpin/p/7019845.html