由于leetCode的IDE是js实现的动态页面,所以不能用FireBug直接审查元素来抓,而是要从发送过来的js代码中抓AC代码。这就意味着需要一个字典来转换特殊字符
def saveCode(code,title):
global mydir
f = open(mydir + title + '.cpp','w')
f.write(code)
def downloadCode(refer,codeadd,title):
global headers
global urlOpener
global myhost
headers['Referer'] = refer
request = urllib2.Request(codeadd,headers=headers)
url = urlOpener.open(request)
all = url.read()
tar = "storage.put('cpp',"
index = all.find(tar,0)
start = all.find('class Solution',index)
finis = all.find("');",start)
code = all[start:finis]
toCpp = {'\u000D':'\n','\u000A':'','\u003B':';','\u003C':'<','\u003E':'>','\u003D':'=',\
'\u0026':'&','\u002D':'-','\u0022':'"','\u0009':'\t','\u0027':"'",'\u005C':'\\'}
for key in toCpp.keys():
code = code.replace(key,toCpp[key])
saveCode(code,title)
def findCode(address,title):
global headers
global urlOpener
global myhost
headers['Referer'] = address
address += 'submissions/'
print 'now is dealing ' + address + ': ' + title
request = urllib2.Request(address,headers=headers)
url = urlOpener.open(request)
all = url.read()
tar = 'class="text-danger status-accepted"'
index = all.find(tar,0)
start = all.find('href="',index)
finis = all.find('">',start)
downloadCode(address,myhost + all[start + 6:finis],title)
def findAdd(page):
index = 0
while 1:
index = page.find('class="ac"',index)
if index != -1:
index += 1
start = page.find('<td><a href="',index)
finis = page.find('">',start)
tmpfin = page.find('<',finis)
title = page[finis + 2:tmpfin]
findCode(myhost + page[start + 13:finis],title)
else:
break