def gethandiTime(soccerid=0):
# url = 'http://www.310win.com/info/1x2exchange.aspx?id=' + str(soccerid) + '&cids=,' + str(companyid) + ',&type=3'
url = 'http://www.310win.com/handicap/' + str(soccerid) + '.html'
soupInstance = SoupHelper(url)
tablelist = soupInstance.gethtmllistwithlabel('table', {'width': '860', 'class':'socai'})
try :
trlist = getelementlistwithlabel(tablelist[0], 'tr')
count = len(trlist)
tr = trlist[count - 1]
if isTagClass(tr):
tdlist = tr.contents
if len(tdlist) > 0:
flag = tdlist[0].get_text()
if flag.strip() != u'' and flag.strip() != u'澳门':
return True
else:
return False
else:
return False
else:
return False
except IndexError as e:
print url
print e
return False
def parserOnePageChannel(self, url):
instance = SoupHelper(url)
ulElement = instance.getOneTagObjWithId('post_container')
# for child in ulElement.descendants:
for child in ulElement.find_all('li'):
thumbnailEle = child.find('div', {'class': 'thumbnail'})
print thumbnailEle.find('a').get('href')
def getImagePages(self):
instance = SoupHelper(self.url)
pageListContainer = instance.getOneTagObjWithClass('div', 'pagelist')
aList = pageListContainer.find_all('a')
for a in aList:
# print a.get('href').encode('utf-8')
self.pageList.append(a.get('href').encode('utf-8'))
def getAllImages(self):
self.imageList = []
for onePage in self.pageList:
soupObj = SoupHelper(onePage)
imgContainer = soupObj.getOneTagObjWithId("post_content")
ele = imgContainer.find_all('img')
for img in ele:
# print img.get('src').encode('utf-8')
self.imageList.append(img.get('src').encode('utf-8'))
def parserAllPages(self, url):
instance = SoupHelper(url)
divElement = instance.getOneTagObjWithClass('div', 'pagination')
if not divElement:
print url + ' 不合法'
print self.pageList
return
pageList = divElement.find_all('a')
lastPage = None
foundNextPageFlag = False
for child in pageList:
pageUrl = child.get('href').encode('utf-8')
# print pageUrl
if not pageUrl in self.pageList:
self.pageList.append(pageUrl)
if child.get_text().encode('utf-8') != '下一页':
lastPage = pageUrl
else:
foundNextPageFlag = True
# print lastPage
if foundNextPageFlag == True:
self.parserAllPages(lastPage)
else:
print self.pageList
#!/usr/bin/env python
# -*- coding: utf-8 -*-
from BEAUTIFUL_SOUP_HELPER import SoupHelper, isTagClass
instance = SoupHelper('http://www.310win.com/info/match/AllScore.aspx')
list = instance.gethtmllistwithlabel('table', options={'id': 'live'})
print instance
def getexchange(soccerid=0):
# url = 'http://www.310win.com/info/1x2exchange.aspx?id=' + str(soccerid) + '&cids=,' + str(companyid) + ',&type=3'
url = 'http://www.310win.com/info/1x2exchange.aspx?id=' + str(
soccerid) + '&cids=,16,18,80,81,90,281,517,545,&type=3'
print url
soupInstance = SoupHelper(url)
trlist = soupInstance.gethtmllistwithlabel('tr', {'bgcolor': '#FFFFFF'})
companieslist = []
colorResultStr = ''
htmlstr = ''
if trlist is None:
return ''
for tr in trlist:
if isTagClass(tr):
oneCompany = BetCompany()
resultStr = tr.get_text('^').encode('utf-8')
unitStrList = resultStr.split('^')
# print resultStr
oneCompany.companyTitle = unitStrList[0]
colorResultStr += unitStrList[0]
colorResultStr += ' 转换后: '
colorResultStr += unitStrList[5]
colorResultStr += ' '
colorResultStr += unitStrList[6]
colorResultStr += ' '
colorResultStr += unitStrList[7]
colorResultStr += ' 实际: '
colorResultStr += unitStrList[9]
colorResultStr += ' '
colorResultStr += unitStrList[10]
colorResultStr += ' '
colorResultStr += unitStrList[11]
colorResultStr += ' '
colorResultStr += '\n'
tdColor = 'white'
titleColor = 'black'
if unitStrList[6] != unitStrList[10]:
tdColor = 'red'
titleColor = 'white'
htmlstr += "<tr bgcolor=\"%s\" style=\"color:%s\"><td>%s</td> <td>%s</td><td>%s</td><td>%s</td>" \
"<td>%s</td><td>%s</td><td>%s</td><td>%s</td><td>%s</td>" % (tdColor,titleColor,oneCompany.companyTitle[:5],
'',unitStrList[5],unitStrList[6],unitStrList[7],
'',unitStrList[9],unitStrList[10],unitStrList[11])
try:
# 胜平负
oneCompany.winOdd = float(unitStrList[1])
oneCompany.drawOdd = float(unitStrList[2])
oneCompany.loseOdd = float(unitStrList[3])
# 转换后的亚盘
oneCompany.exchange_top = float(unitStrList[5])
# oneCompany.exchange_Handicap = switchHandicap(unitStrList[6])
oneCompany.exchange_bottom = float(unitStrList[7])
# 当前的亚盘
oneCompany.now_top = float(unitStrList[8])
# oneCompany.now_Handicap = switchHandicap(unitStrList[9])
oneCompany.now_top = float(unitStrList[10])
except BaseException as e:
print e
else:
companieslist.append(oneCompany)
print "\033[1;31;40m%s\033[0m" % colorResultStr
return htmlstr
# if sys.argv.__len__()==1:
# sys.exit('\033[0;36;40m使用说明:\n1个参数:\n事例: python TodaySoccer.pyc 12344\033[0m')
#
# if __name__ == '__main__':
# getexchange(sys.argv[1])
# getexchange(1444073)