def panel(url):
link=araclar.get_url(web)
soup=BS(link.decode('utf-8','ignore'))
div = soup.findAll("div",{"class":"blok-liste"})
for li in div[int(url)].findAll('li'):#-------------dizi anasayfalari bulur
url= li.a['href']
name = li.a.text
name=name.encode("utf-8")
araclar.addDir(fileName,name,"kategoriler(url)",url,"YOK")
def run(self):
#resp = urllib2.urlopen(self.url)
#print self.url, resp.getcode()
req = urllib2.Request(url=self.url,headers=headers)
content = urllib2.urlopen(req)
soup = BeautifulSOAP(content,fromEncoding="gb18030")
#print soup.originalEncoding
#print soup.prettify()
songlist = soup.findAll('a',{'href':re.compile(r'/song/(\d)+')})
#print dir(songlist[0])
for song in songlist:
song_url=''
song_url= 'www.xiami.com' + song.get('href')
print song_url ,song.string
def geturladdress(keywords,type,number,filename):
urltitle = {}
pageid = string.atoi(number)/100
for idpage in range(0,pageid,1):
entirehtml= getresponse(keywords,type,idpage*100)
soup = BeautifulSOAP(entirehtml)
results = soup.findAll('li', {'class': 'g'})
for result in results:
title_a = result.find('a')
if not title_a:
continue
else:
title = ''.join(title_a.findAll(text=True))
title = html_unescape(title)
#print title
url = title_a['href']
#print url
url = getdomain(url)
urltitle[title]= url
writetofile(filename,urltitle)
def geturladdress(keywords, type, number, filename):
urltitle = {}
pageid = string.atoi(number) / 100
for idpage in range(0, pageid, 1):
entirehtml = getresponse(keywords, type, idpage * 100)
soup = BeautifulSOAP(entirehtml)
results = soup.findAll('li', {'class': 'g'})
for result in results:
title_a = result.find('a')
if not title_a:
continue
else:
title = ''.join(title_a.findAll(text=True))
title = html_unescape(title)
#print title
url = title_a['href']
#print url
url = getdomain(url)
urltitle[title] = url
writetofile(filename, urltitle)
import re,urllib,urllib2
from BeautifulSoup import BeautifulSOAP
url= 'http://www.xiami.com/artist/top/id/1234'
headers = {'User-Agent':"Mozilla/5.0 (Windows NT 5.1; rv:27.0) Gecko/20100101 Firefox/27.0"}
req = urllib2.Request(url=url,headers=headers)
content = urllib2.urlopen(req)
soup = BeautifulSOAP(content,fromEncoding="gb18030")
#print soup.originalEncoding
#print soup.prettify()
songlist = soup.findAll('a',{'href':re.compile(r'/song/(\d)+')})
#print dir(songlist[0])
for song in songlist:
song_url=''
song_url= 'www.xiami.com' + song.get('href')
print song_url ,song.string
#songlist = re.findall(pattern,string)
#songlist = re.findall(pattern,content)
#for song in songlist:
# print song
#
print "end"
