def get500wwcbf(self, url):
print("获取500w比赛昨日完场比分数据" + url)
htmltext = getHtml().getHtml_by_firefox(url)
soup = BeautifulSoup(htmltext, 'html5lib')
listtable = soup.find_all(id='table_match')
list31 = listtable[0].find_all('tr')
bsxxlist = []
zqdf = zqconfigClass('').cfg_select()
li = zqdf.ls.values
for x in list31:
id12 = (x.get('id'))
if id12 == None: continue
id1 = id12[1:]
idlist = []
idlist.append(id1)
#获取联赛的球队
listgy = (x.get('gy').split(','))
if listgy[0] not in li: continue
if listgy[0].find('女') > -1: continue
if listgy[0].find('U') > -1: continue
if listgy[0].find('丙') > -1: continue
listgy.extend(idlist)
bsxxlist.append(listgy)
return bsxxlist
def _gethtmlsoup(self, url):
#500w北单比方情况
#url="https://live.500.com/zqdc.php"
#url="https://live.500.com/2h1.php"
htmltext = getHtml().getHtml_by_firefox(url)
soup = BeautifulSoup(htmltext, 'html5lib')
return soup
def getqtzqdc(self):
print("获取球探当日比赛单场数据")
h = getHtml()
htmltext = h.getHtml_by_firefox(
"http://live.win007.com/index2in1.aspx?id=8")
soup = BeautifulSoup(htmltext, 'lxml')
#获取主要表格
ss = soup.find_all('table', id="table_live")
list2 = []
for tb in ss[0:2]:
row = tb.find_all("tr")
for cell in row:
cc = cell.find_all('td')
#去除干扰
if len(cc) < 2: continue
i = 0
list1 = []
for x in cc:
i += 1
xstr = x.text
if xstr == '选': break
if xstr == '': xstr = '-'
if cc.index(x) == 9:
#print(i,cc.index(x),x)
xstr = x.find_all('div', attrs={'class':
'odds1'})[0].text
list1.append(xstr)
if len(list1) > 1:
list2.append(list1)
#print(list2[1:3])
#获取配置文件上的比赛列表
#zqdf=zqconfigClass('').cfg_select()
#li=zqdf.ls.values
#
list5 = []
for x in iter(list2):
#提出不需要的比赛
#if x[1] not in li:continue
#if x[5]!='-':continue#未开场
#if x[9]!='半球':continue#半球
list4 = []
list4.append(x[1])
list4.append(x[4])
list4.append(x[6])
list4.append(x[2])
list4.append(x[5])
list4.append(x[9])
list5.append(list4)
return list5
def _gethtmlsoup_oz(self, url):
htmltext = getHtml().getHtml_by_firefox2(url, 7)
soup = BeautifulSoup(htmltext, 'html5lib')
return soup