예제 #1
0
 def __init__(self):
     self.start_pointer = self.startpointer()
     self.proxy = ''
     self.a = buildPP()
     self.pp = self.a.getpp(3)
     self.ppointer = self.getppointer()
     self.proxy_usetime = 0
     self.changep()
     self.crawlli = []
예제 #2
0
 def __init__(self):
   self.start_pointer = self.startpointer()
   self.proxy=''
   self.a = buildPP()
   self.pp = self.a.getpp(3)
   self.ppointer = self.getppointer()
   self.proxy_usetime = 0
   self.changep()
   self.crawlli=[]
예제 #3
0
 def __init__(self):
     self.proxy=''
     self.a = buildPP()
     self.pp = self.a.getpp(3)
     self.ppointer = self.getppointer()
     self.proxy_usetime = 0
     self.changep()
     self.pointer = self.startpointer()-1
     self.begin = True
     self.requestpool = []
     self.genewrequest()        
예제 #4
0
 def __init__(self):
     self.proxy = ''
     self.a = buildPP()
     self.pp = self.a.getpp(3)
     self.ppointer = self.getppointer()
     self.proxy_usetime = 0
     self.changep()
     self.pointer = self.startpointer() - 1
     self.begin = True
     self.requestpool = []
     self.genewrequest()
예제 #5
0
    def __init__(self):
      self.timepointer = int(time.clock())
      self.proxy=''
      self.a = buildPP()
      self.pp = self.a.getpp(3)
      self.ppointer = self.getppointer()
      self.proxy_usetime = 0
      self.changep()

      self.aidpointer = self.startpointer() - 1
      self.crawlli=[]
      self.startrequests = self.start_next(self.aidpointer)
예제 #6
0
    def __init__(self):
      self.timepointer = int(time.clock())
      self.proxy=''
      self.a = buildPP()
      self.pp = self.a.getpp(3)
      self.ppointer = self.getppointer()
      self.proxy_usetime = 0
      self.changep()

      self.aidpointer = self.startpointer() - 1
      self.crawlli=[]
      self.startrequests = self.start_next(self.aidpointer)
예제 #7
0
 def __init__(self):
   self.aidpointer = self.startpointer()
   self.start_aid = PriorityPeople[self.aidpointer]#self.def_start_id()
   self.authorname = self.aname(self.start_aid)   
   self.authornameList = self.seperateName(self.authorname)
   self.initial(self.authorname,self.start_aid,self.authornameList)
   self._authornameList = self.ListChange(self.authornameList)
   self.start_urls = ["http://scholar.google.com/scholar?hl=en&num=100&as_sdt=0,5&q=%s"%s for s in self._authornameList]
   
   self.timepointer = int(time.clock())
   self.crawled_id=[]
   self.pages = 0
   self.proxy=''
   self.a = buildPP()
   self.pp = self.a.getpp(4)
   self.ppointer_test = self.getppointer()
   self.proxy_usetime = 0
   self.changep()
   self.crawlli=[]