API tools faq
paste
Advertisement
s243a

PT Bookmark Parser

s243a
Dec 6th, 2018
247
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 4.60 KB | None | 0 0
raw download clone embed print report
  1. import sgmllib, urllib, urlparse, os, pickle
  2. class HTML_Link:
  3.     def __init__(self,**kw):
  4.         self.text=kw.get("text"," ")
  5.         self.href=kw.get("href",'/')
  6.         self.add_date=kw.get("add_date",'0')
  7.         self.linkType=kw.get("linkType",None)
  8.  
  9.     def toHTML(self):
  10.        
  11.         if self.linkType is None:
  12.             str='<A HREF="'+self.href+'" ADD_DATE="'+self.add_date+'">'+self.text+"</A>"
  13.             return str
  14.         elif self.linkType.upper()=="FOLDER":
  15.             str='<A HREF="'+self.href+'">'+self.text+"</A>"          
  16.             return '<b>Folder:</b>'+str
  17. class Section:
  18.     def __init__(self,text):
  19.         self.text=text
  20.     def toHTML(self):
  21.         return "<H3>"+self.text+"</H3>"
  22. class BookMarkParser(sgmllib.SGMLParser):
  23.     def __init__(self,**kw):
  24.         sgmllib.SGMLParser.__init__(self)
  25.         self.STATE="__init__"
  26.         self.DL=[]
  27.         self.items=[]
  28.         self.wd=kw.get('wd','/root/Downloads/pt')
  29.         if not os.path.exists(self.wd):
  30.             print("Making directory "+self.wd)
  31.             os.makedirs(self.wd)
  32.     def writeHTMLHeader(self,f):
  33.         print('WriteHTMLHeader')
  34.         f.write("%s\n" % '<!DOCTYPE html>')
  35.         f.write("%s\n" % '<html>')
  36.         f.write("%s\n" % '<body>')
  37.     def writeHTMLFooter(self,f):
  38.         print('writeHTMLFooter')
  39.         f.write("%s\n" % '</body>')        
  40.         f.write("%s\n" % '</html>')  
  41.     def writeList(self):
  42.         print('writeList')
  43.         with open('index.html', 'w') as f:
  44.             self.writeHTMLHeader(f)
  45.             for item in self.items:
  46.                 if item is not None:
  47.                     f.write("%s\n" % item.toHTML())
  48.                 else:
  49.                     f.write("<b>Empty Item!!!!</b>")
  50.                
  51.             self.writeHTMLFooter(f)
  52.     def storeList(self):
  53.         print('storeList')
  54.         os.chdir(self.wd)
  55.         print(os.getcwd())
  56.         self.wd=os.getcwd()
  57.         pickle.dump(self.items,open( "list.p", "wb" ))
  58.     def loadList(self):
  59.         print('loadList')
  60.         os.chdir(self.wd)
  61.         print(self.wd)
  62.         print(os.getcwd())
  63.         self.items=pickle.load(open( "list.p", "rb" ))
  64.     def start_h3(self, attributes):
  65.         print('start_H3')
  66.         self.STATE='Started H3'
  67.         for name, value in attributes:
  68.             print(name+"="+value)
  69.             if (value == 'FOLDED') or (name == 'folded'):
  70.                 self.STATE='FOLDED'
  71.     def handle_data(self,data):
  72.         print('handleData')
  73.         print("self.STATE="+self.STATE)
  74.         if self.STATE=='FOLDED':
  75.             dirname = urllib.quote(data, safe='')
  76.             dirname2= urllib.quote(dirname, safe='')
  77.             self.items.append(HTML_Link(href=dirname2+"/index.html",linkType='FOLDER',text=data))
  78.             self.storeList()
  79.             self.wd=os.path.join(self.wd,dirname)
  80.             print("self.wd="+self.wd)
  81.             #https://stackoverflow.com/questions/273192/how-can-i-safely-create-a-nested-directory-in-python
  82.             if not os.path.exists(self.wd):
  83.                 print("Making directory "+self.wd)
  84.                 os.makedirs(self.wd)
  85.             print("Entering:" + str(self.wd))
  86.             self.STATE="Seeking DL"
  87.  
  88.         if self.STATE=="A":
  89.            
  90.             self.A.text=data
  91.         if self.STATE=="DD":
  92.             self.items.append(Section(data.split('\n')[0]))
  93.     def end_h3(self): #Probably redundant
  94.         print('end_H3')
  95.         self.FOLDED=False        
  96.     def start_dl(self, atributes):
  97.         print('start_DL')
  98.         self.items=[]
  99.         print(self.DL)
  100.         print(self.wd)
  101.         self.DL.append(os.path.basename(self.wd)) #Maybe append the full path here instead of the basename
  102.     def end_dl(self):
  103.         print('end_DL')
  104.         self.writeList()
  105.         self.DL.pop
  106.         self.wd=os.path.join(self.wd,"..")
  107.         self.loadList()
  108.        
  109.     def start_a(self,atributes):
  110.         print('start_A')
  111.         self.A=HTML_Link()
  112.         for key,value in atributes:
  113.            setattr(self.A,key,value)
  114.         self.STATE='A'
  115.     def end_a(self):
  116.         print('end_A')
  117.         self.items.append(self.A)
  118.         self.A=None
  119.         self.STATE='Ended A'
  120.     def do_dd(self, atributes):
  121.         print('do_DD')
  122.         self.STATE="DD"
  123.     def do_dt(self, atributes):
  124.         print('do_DT')
  125.         self.STATE="DT"
  126. p = BookMarkParser()
  127. filename='/root/Downloads/pearltrees_export.html'
  128. f = open(filename, "r")
  129. BUFSIZE = 8192
  130. while True:
  131.     #data = f.read(BUFSIZE)
  132.     data=f.readline()
  133.     print('data='+str(data))
  134.     if not data: break
  135.     p.feed(data)
  136. p.close(  )
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!