API tools faq
paste
Advertisement
Arusekk

librus.py

Arusekk
May 3rd, 2016
250
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 20.09 KB | None | 0 0
raw download clone embed print report
  1. #!/usr/bin/python
  2. # -*- coding: utf -*-
  3.  
  4. import code, urllib, urllib2, os, sys, re, cookielib, time, traceback
  5. import glob
  6. try:
  7.   from bazaocen import baza
  8. except:
  9.   baza=[]
  10. from HTMLParser import HTMLParser
  11. from htmlentitydefs import name2codepoint
  12. from email.header import make_header
  13. from subprocess import *
  14.  
  15. cookielib.debug = True
  16.  
  17. #librfmt='%F'
  18. librfmt='%Y-%m-%d'
  19. rfc822fmt='%a, %e %b %Y %T %z'
  20.  
  21. class MyCookiePolicy(cookielib.DefaultCookiePolicy):
  22.     def set_ok(self, cookie, request):
  23.     return True
  24.  
  25. class RedirHandler(urllib2.HTTPRedirectHandler):
  26.     def redirect_request(self, oldreq, fp, code, msg, hdrs, newurl):
  27.     global req
  28.     #print (req,fp,code,msg,hdrs,newurl)
  29.     jar.extract_cookies(fp,oldreq)
  30.     if url.find('?')!=-1:
  31.       newurl+=url[url.find('?'):]
  32.     req=urllib2.Request(newurl, None, hdrs)
  33.     jar.add_cookie_header(req)
  34.         return req
  35.  
  36. cookiefn='kukis.txt'
  37. jar=cookielib.MozillaCookieJar(cookiefn,True)#,MyCookiePolicy)
  38.  
  39. direct=urllib2.build_opener(RedirHandler)
  40.  
  41. host = "synergia.librus.pl"
  42. site = 'https://%s/loguj/przenies'%host
  43. username = '1234567u'
  44. password = '#jestembogiem'
  45. url = site + '/przegladaj_oceny/uczen'
  46. headers = {
  47. "User-Agent" : "Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Firefox/31.0",
  48. "Host" : host,
  49. "Referer" : url,
  50. "Connection" : "keep-alive",
  51. "Cache-Control" : "max-age=0",
  52. "Accept-Language" : "pl,en-us;q=0.7,en;q=0.3",
  53. "Accept-Encoding" : "gzip, deflate",
  54. "Accept" : "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
  55. #"Accept-Charset" : "utf-8,ISO-8859-2;q=0.8,*;q=0.7"
  56. }
  57. data = [
  58. ("login",username),
  59. ("passwd",password),
  60. ("czy_js",1)
  61. ]
  62. fn='result.html'
  63.  
  64.  
  65. def safemakeheaderu8(t, quoted=''):
  66.     try:
  67.     return quoted+make_header([(t,'ascii')]).encode()+quoted
  68.     except:
  69.     return make_header([(t,'utf-8')]).encode()
  70.  
  71. def dodal(entry):
  72.     x=entry.get('Dodał'.decode('utf'), 'NIEDODAŁ2').split('(')[0].strip()
  73.     return x.split(' ')[-1],' '.join(x.split(' ')[:-1])
  74.  
  75. def glue(L):
  76.     ret=''
  77.     prev='\n'
  78.     for i in L:
  79.     if prev.endswith('\n') or i.startswith('\n'):
  80.         pass
  81.     else:
  82.         ret+='\n'
  83.     try:
  84.         ret+=i
  85.     except UnicodeDecodeError,e: # why?! all items are str
  86.         try:
  87.         ret+=repr(i.replace(u'\xa0',' '))[2:-1]
  88.         except UnicodeDecodeError,e2:
  89.         print "UnicodeDecodeError:",e
  90.         ret+="<really stupid unicode text>"
  91.     prev=i
  92.     return (ret[:-1] if ret.endswith('\n') else ret)
  93.  
  94. def attrfmt(x):
  95.     x=list(x)
  96.     if x[1]==None: x[1]=''
  97.     x[1]=x[1].replace('&','&amp;').replace('"','&quot;').encode('ascii', 'xmlcharrefreplace')
  98.     return str(' %s="%s"'%tuple(x))
  99.  
  100.  
  101. def wrap_HTML(x):
  102.     return '''
  103. <!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0//EN" "http://www.w3.org/TR/REC-html40/strict.dtd">
  104. <html><head><meta name="qrichtext" content="1" /><style type="text/css">
  105. p, li { white-space: pre-wrap; }
  106. table { border: 3px outset; }
  107. th, td { border: 3px inset; }
  108. th { text-align: right; }
  109. </style></head><body><table border="3">
  110. %s
  111. </table></body></html>
  112. '''%(x.replace('\r\n',' ').replace('  ',' ').replace('  ',' ').replace('  ',' ').replace('> <','><'))
  113.  
  114.  
  115.  
  116. def update():
  117.     global req,fn,url
  118.     headers['Referer'] = url
  119.     postdata = urllib.urlencode(dict(data))
  120.     req = urllib2.Request(url, postdata, dict(headers))
  121.     jar.add_cookie_header(req)
  122.     h = req.get_header('Cookie')
  123.     if h and h.find('DZIENNIKSID') != -1:
  124.       url = url.replace('/loguj/przenies','')
  125.       req = urllib2.Request(url, None, dict(headers))
  126.     jar.add_cookie_header(req)
  127.     print ('Sent headers are: {')
  128.     for it in req.header_items():
  129.     print ('%20r: %r'%it)
  130.     print ('}')
  131.     response = direct.open(req)
  132.     jar.extract_cookies(response,req)
  133.     print ('url is %s'%response.geturl())
  134.     print ('Received headers are: {')
  135.     for it in response.info().items():
  136.     print ('%20r: %r'%it)
  137.     print ('}')
  138.     if response.info().get("transfer-encoding")=='gzip':
  139.     fn+='.gz'
  140.     if response.info().get("content-encoding")=='gzip':
  141.     fn+='.gz'
  142.     with open(fn, 'w+b') as fp:
  143.     buff=response.read(1024)
  144.     while buff!='':
  145.         fp.write(buff)
  146.         buff=response.read(1024)
  147.     response.close()
  148.     if fn.endswith('.gz'):
  149.     Popen(["gunzip","-f",fn]).wait()
  150.     fn=fn[:-3]
  151.     print ('done')
  152.  
  153.  
  154. def get_details(href):
  155.     global fn,url
  156.     oldfn,fn=fn,'oceny_szczegoly/%s.html'%(href.split('/')[-1])
  157.     url = site + href
  158.     if not os.path.isfile(fn):
  159.     update()
  160.     try:
  161.       ret=parse2()
  162.     except:
  163.       print "plik problemu:",fn
  164.       raise
  165.     fn=oldfn
  166.     return ret
  167.  
  168.  
  169. #def get_msg(href):
  170.     #global fn,url
  171.     #oldfn,fn=fn,'msg_szczegoly/%s.html'%(href.split('/')[-1])
  172.     #url = site + href
  173.     #if not os.path.isfile(fn):
  174.     #update()
  175.     #ret=parse2()
  176.     #fn=oldfn
  177.     #return ret
  178.  
  179.  
  180.  
  181.  
  182. class MyHTMLNode(object):
  183.     MX_CONTENT_LEN=16
  184.     problem=[]
  185.     def __init__(self):
  186.     self.parentNode=None
  187.     self.childNodes=[]
  188.     def appendChild(self, elem, idx=None):
  189.     if isinstance(elem, MyHTMLData):
  190.         if self.childNodes and isinstance(self.childNodes[-1], MyHTMLData):
  191.         self.childNodes[-1].dane+=elem.dane
  192.         return
  193.     if idx is None:
  194.         self.childNodes.append(elem)
  195.     else:
  196.         self.childNodes.insert(idx,elem)
  197.     elem.parentNode=self
  198.     if hasattr(elem, 'event'):
  199.         elem.event()
  200.     def _HTML(self):
  201.     raise NotImplementedError
  202.     def __repr__(self):
  203.     #return "<%s%s at 0x%x%s%s>"%(self.nodeName+' ' if isinstance(self,MyHTMLElement) else "",type(self).__name__,id(self),", whose attrs=%r"%dict(self.attrs) if isinstance(self,MyHTMLElement) and self.attrs else "",", whose childNodes=%r"%self.childNodes if self.childNodes else '')
  204.     return "<%s%s at 0x%x%s%s>"%(self.nodeName+' ' if isinstance(self,MyHTMLElement) else "",type(self).__name__,id(self),", whose attrs=%r"%dict(self.attrs) if isinstance(self,MyHTMLElement) and self.attrs else ""," with childNodes" if self.childNodes else '')
  205.     HTML=property(lambda self:self._HTML())
  206.  
  207. class MyHTMLElement(MyHTMLNode):
  208.     tables=[]
  209.     def __init__(self,nodeName,attrs):
  210.     MyHTMLNode.__init__(self)
  211.     self.nodeName=nodeName
  212.     self.attrs=attrs
  213.     if nodeName=='document':
  214.         del self.tables[:]
  215.     if nodeName=='table':
  216.         self.tables.append(self)
  217.         self.tbody = self
  218.     if nodeName=='a':
  219.         href=dict(attrs).get('href','')
  220.         if href.startswith('/przegladaj_oceny/szczegoly/') and href not in oceny_ids:
  221.         oceny_ids.append(href)
  222.     def event(self):
  223.     if self.nodeName in ('thead','tbody','tfoot'):
  224.         setattr(self.parentNode, self.nodeName, self)
  225.     elif self.nodeName=='a':
  226.         magia="otworz_w_nowym_oknie('/zapytaj_nauczyciela/"
  227.         magia2="', 'ask',700,600)"
  228.         onclick=dict(self.attrs).get('onclick','')
  229.         if onclick.startswith(magia) and onclick.endswith(magia2):
  230.         tree=self.parentNode
  231.         while tree.nodeName!='document':
  232.             tree=tree.parentNode
  233.         nau=MyHTMLElement('nauczyciel',[])
  234.         nau.appendChild(MyHTMLData(onclick[len(magia):-len(magia2)]))
  235.         tree.appendChild(nau,0)
  236.     def _innerHTML(self,indent=0):
  237.       return glue(map(lambda x:x._HTML(indent+1), self.childNodes)).replace('\n','\n'+'  ') #*indent)
  238.     innerHTML=property(_innerHTML)
  239.     def _HTML(self, indent=0):
  240.     try:
  241.         innerHTML=self._innerHTML(indent)
  242.         if len(innerHTML)>self.MX_CONTENT_LEN: innerHTML='\n  %s\n'%innerHTML
  243.         if innerHTML or self.nodeName not in ("link","meta","img"):
  244.         ret='<%s%s>%s</%s>'% \
  245.               (self.nodeName,''.join(map(attrfmt,self.attrs)),innerHTML,self.nodeName)
  246.         else:
  247.         ret='<%s%s />'% \
  248.               (self.nodeName,''.join(map(attrfmt,self.attrs)) )
  249.         #assert type(ret)==str, "Stupid automatic conversion"
  250.         return ret
  251.     except:
  252.         if not self.problem:
  253.         print ("stupid ascii detected in %r"%self)
  254.         self.problem.append(self)
  255.         raise
  256.  
  257. class MyHTMLData(MyHTMLNode):
  258.     nodeName=property(lambda self:type(self).__name__)
  259.     def __init__(self,dane):
  260.     MyHTMLNode.__init__(self)
  261.         ret=''
  262.     for c in dane:
  263.         try:
  264.           ret+=c
  265.           #assert type(ret)==str
  266.         except:
  267.           ret+='~~'
  268.     self.dane=ret
  269.     def _HTML(self, indent=0):
  270.     x=self.dane.replace('\n','\n'+'  ') #*indent)
  271.     #if x.startswith('Doda'):
  272.       #print "Doda?",x,type(x)
  273.     return x
  274.  
  275. class MyHTMLComment(MyHTMLData):
  276.     def _HTML(self, indent=0):
  277.     return '<!--%s-->'%self.dane.replace('\n','\n'+'  ') #*indent)
  278.  
  279. class MyHTMLDecl(MyHTMLData):
  280.     def _HTML(self, indent=0):
  281.     return '<!%s>'%self.dane.replace('\n','\n'+'  ') #*indent)
  282.  
  283. class MyHTMLPI(MyHTMLData):
  284.     def _HTML(self, indent=0):
  285.     return '<?%s>'%self.dane.replace('\n','\n'+'  ') #*indent)
  286.  
  287.  
  288. class MyHTMLParse(HTMLParser):
  289.     good1=[
  290.         ('html', {}), ('body', {'onload': 'ImageSwaper.GetInstance().Load(); '}), ('div', {'id': 'page'}), ('div', {'id': 'body'}), ('form', {'action': '/przegladaj_oceny/uczen', 'method': 'POST', 'name': 'PrzegladajOceny'}),
  291.         ('div', {'class': 'container'}), ('div', {'class': 'container-background'}), ('table', {'class': 'decorated stretch'}), ('tr', {'class': 'line0'}), ('td', {})
  292.           ]
  293.     good2=good1[:]
  294.     good2[-2]=('tr',{'class':'line1'})
  295.     autoclose=set(["img","link","meta","br","hr"])
  296.     def __init__(self, typ=0, *args, **arg2):
  297.     self.typ=typ
  298.     HTMLParser.__init__(self,*args,**arg2)
  299.     self.stack=[]
  300.     self.tree=self.curr_elem=MyHTMLElement("document",[])
  301.     self.lastx="line1"
  302.     self.happened=False
  303.  
  304.     def handle_starttag(self, tag, attrs):
  305.     if self.curr_elem.nodeName in self.autoclose: self.handle_endtag(self.curr_elem.nodeName)
  306.     elem=MyHTMLElement(tag,attrs)
  307.     self.curr_elem.appendChild(elem)
  308.     self.curr_elem=elem
  309.     self.happened=True
  310.     flag=(self.typ==0 and self.isok())
  311.     self.stack.append((tag,dict(attrs)))
  312.     if self.typ==0 and self.isok():
  313.         if flag:
  314.         self.fp2.write('","<%s%s>'%
  315.             (tag,''.join(map(lambda x:' %s="%s"'%x,attrs)))
  316.             )
  317.         else:
  318.         if oceny:
  319.             #oceny[-1][-1].pop()
  320.             oceny[-1]+=([],)
  321.         self.fp2.write('","###')
  322.  
  323.     def handle_endtag(self, tag):
  324.     self.happened=True
  325.     flag=self.isok()
  326.         if tag in map(lambda x:x[0],self.stack):
  327.         self.curr_elem=self.curr_elem.parentNode
  328.         x=self.stack.pop()[0]
  329.         while x!=tag:
  330.         #print ("Auto-closing unclosed tag of %s"%x)
  331.         self.curr_elem=self.curr_elem.parentNode
  332.         x=self.stack.pop()[0]
  333.     else:
  334.         pass#print ("Closed unopen tag of %s"%tag)
  335.     if self.typ==0 and flag:
  336.         if self.isok():
  337.         self.fp2.write('","</%s>'%tag)
  338.         else:
  339.         self.fp2.write('"\n"%%%')
  340.  
  341.     def handle_entityref(self, name):
  342.         c = unichr(name2codepoint.get(name,0))
  343.         if c == '\0':
  344.       print "&%s; -> &#x%x;"%(name,ord(c))
  345.         self.handle_data(c,True,name)
  346.  
  347.     def handle_charref(self, name):
  348.         if name.startswith('x'):
  349.             c = unichr(int(name[1:], 16))
  350.         else:
  351.             c = unichr(int(name))
  352.         #print "&#%s; -> &#x%x;"%(name,ord(c))
  353.         self.handle_data(c,True,"#"+name)
  354.  
  355.     def handle_data(self, dane, special=False, ent=None):
  356.     if self.curr_elem.nodeName in self.autoclose: self.handle_endtag(self.curr_elem.nodeName)
  357.     if self.curr_elem.nodeName!="script":
  358.         dane=dane.replace('\n',' ').replace('  ',' ').replace('  ',' ').replace('  ',' ').replace('  ',' ').replace('  ',' ')
  359.     if  True or not special:
  360.         danne=MyHTMLData(dane)
  361.     else:
  362.         danne=MyHTMLData("&%s;"%ent)
  363.     self.curr_elem.appendChild(danne)
  364.     if self.typ==0 and self.isok():
  365.         if self.happened:
  366.         if self.lastx!=self.stack[len(self.good1)-2][1]['class']:
  367.             if oceny:
  368.             oceny[-1]=oceny[-1][:1]+oceny[-1][2:-1]
  369.             oceny.append((dane,[]))
  370.             self.fp2.write('"\n"')
  371.             self.lastx=self.stack[len(self.good1)-2][1]['class']
  372.         else:
  373.             self.fp2.write('","')
  374.         oceny[-1][-1].append('')
  375.         self.happened=False
  376.         if special:
  377.         if ord(dane)==0xa0:
  378.             oceny[-1][-1][-1]+=' '
  379.             self.fp2.write(' ')
  380.         else:
  381.             oceny[-1][-1][-1]+='&#x%x;'%ord(dane)
  382.             self.fp2.write('&#x%x;'%ord(dane))
  383.         else:
  384.         oceny[-1][-1][-1]+=dane
  385.         self.fp2.write(dane)
  386.  
  387.     def handle_decl(self, dane):
  388.     decl=MyHTMLDecl(dane)
  389.     if self.curr_elem.nodeName in self.autoclose: self.handle_endtag(self.curr_elem.nodeName)
  390.     self.curr_elem.appendChild(decl)
  391.  
  392.     def handle_pi(self, dane):
  393.     pi=MyHTMLPI(dane)
  394.     if self.curr_elem.nodeName in self.autoclose: self.handle_endtag(self.curr_elem.nodeName)
  395.     self.curr_elem.appendChild(pi)
  396.  
  397.     def handle_comment(self, comm):
  398.     comment=MyHTMLComment(comm)
  399.     if self.curr_elem.nodeName in self.autoclose: self.handle_endtag(self.curr_elem.nodeName)
  400.     self.curr_elem.appendChild(comment)
  401.  
  402.     def isok(self):
  403.     for i in range(len(self.stack)):
  404.         if i>=len(self.good1):
  405.         return True
  406.         if self.stack[i]==self.good1[i]:
  407.         pass
  408.         elif self.stack[i][0]!=self.good1[i][0]:
  409.         return False
  410.         elif self.stack[i]!=self.good2[i]:
  411.         return False
  412.     else:
  413.         if len(self.stack)==len(self.good1):
  414.         return True
  415.     return False
  416.  
  417. def parse():
  418.     global oceny, oceny_ids
  419.     oceny=[]
  420.     oceny_ids=[]
  421.     parser=MyHTMLParse()
  422.     with open(fn,'rt') as fp, open(os.path.splitext(fn)[0]+".csv",'wb') as parser.fp2:
  423.     parser.fp2.write('"Wyciąg z Librusa')
  424.     buff=fp.read(1024)
  425.     while buff!='':
  426.         buff=buff.replace('> <','><').replace('>\r\n<','><')
  427.         while ord(buff[-1])>127:
  428.           buff+=fp.read(1)
  429.         parser.feed(buff.decode('utf'))
  430.         buff=fp.read(1024)
  431.     parser.fp2.write('"\n')
  432.     #oceny=dict(oceny)
  433.     #oceny: <p class="... ..." ...><a title="WAZNE..." class="..." ...>6+</a></p>
  434.     with open(fn+".html",'wb') as fp:
  435.     x=parser.tree.innerHTML
  436.     x=x.replace('\r\n','\n').replace('\r','\n').replace('\n','\r\n').replace('\n\t\t','\n'+' '*16).replace('\n\t','\n'+' '*8)
  437.     for i in range(40):
  438.       for j in range(2):
  439.         x=x.replace('\n'+' '*i+'\r\n','\n')
  440.     fp.write(x.encode('utf'))
  441.  
  442. def parse3():
  443.     # var chartDataGradeAverangeGraphDiv = [
  444.     parser=MyHTMLParse(1)
  445.     with open(fn,'rt') as fp:
  446.     buff=fp.read(1024)
  447.     while buff!='':
  448.         buff=buff.replace('> <','><').replace('>\r\n<','><')
  449.         while ord(buff[-1])>127:
  450.           buff+=fp.read(1)
  451.         parser.feed(buff.decode('utf'))
  452.         buff=fp.read(1024)
  453.     tree=parser.tree
  454.     txt=tree.childNodes[1].innerHTML
  455.     txt='field='+txt[txt.find('['):txt.find(']')+1]
  456.     d={'columnGradeAverangeGraphDiv':'d','x0':'u','x1':'c','__builtins__':None}
  457.     exec txt in d
  458.     return d['field'] #[{'d':x['d'],'u':d['u'],'c':d['c']} for x in d['field']]
  459.  
  460. def parse2():
  461.     parser=MyHTMLParse(1)
  462.     with open(fn,'rt') as fp:
  463.     buff=fp.read(1024)
  464.     while buff!='':
  465.         buff=buff.replace('> <','><').replace('>\r\n<','><')
  466.         while ord(buff[-1])>127:
  467.           buff+=fp.read(1)
  468.         parser.feed(buff.decode('utf'))
  469.         buff=fp.read(1024)
  470.     #magic_idxes=[2,2,10,3,5,0,3,0,3]
  471.     #magic_nodnams_wzorzec=['html','body','div','div','form','div','div','table','tbody']
  472.     tree=parser.tree
  473.     #magic_nodnams=[]
  474.     #for i,j in zip(magic_idxes,magic_nodnams_wzorzec):
  475.     #magic_nodnams.append(tree.nodeName)
  476.     #try:
  477.       #if i<len(tree.childNodes) and tree.childNodes[i].nodeName==j:
  478.         #tree=tree.childNodes[i]
  479.       #elif i+1<len(tree.childNodes) and tree.childNodes[i+1].nodeName==j:
  480.         #tree=tree.childNodes[i+1]
  481.         #print ('Warn: num for %r is now %r'%(j,i+1) )
  482.       #else:
  483.         #print ('Mistyped num for %r=%r; it\'s instead=%r'%(j,i,tree.childNodes[i] if i<len(tree.childNodes) else Ellipsis) )
  484.         #for isitok,indeks in zip(tree.childNodes, range(len(tree.childNodes)) ):
  485.           #if isitok.nodeName==j:
  486.         #tree=isitok
  487.         #print ('Gut num is %r [%r]'%(indeks,fn) )
  488.         #break
  489.         #else:
  490.           #print ('so far magic_nodnams=%r; librus ma problem z %r'%(magic_nodnams,fn))
  491.     #except:
  492.       #print ('so far magic=%r'%tree)
  493.       #raise
  494.     #print ('magic_nodnams=%r'%magic_nodnams)
  495.     if len(tree.tables)<1:
  496.       print "#err in %s"%fn
  497.       return NotImplemented
  498.     tree = tree.tables[-1].tbody
  499.     #print tree, tree.childNodes
  500.     outree={}
  501.     for i in tree.childNodes:
  502.     if i.nodeName=='tr':
  503.         tdtd=thth=''
  504.         for x in i.childNodes:
  505.         if x.nodeName=='td' and not thth:
  506.             x.nodeName='th'
  507.         if x.nodeName=='th':
  508.             thth=x.innerHTML.strip()
  509.         elif x.nodeName=='td':
  510.             tdtd=x.innerHTML.replace('\n ','\n').replace('\n','').replace('\r','').strip()
  511.         outree[thth]=tdtd
  512.     outree.setdefault('Ocena','BR')
  513.     outree.setdefault('Przedmiot','BRAK')
  514.     outree.setdefault(u'Dodał','BRAK')
  515.     outree.setdefault('Data','1999-11-11')
  516.     if len(outree.get('Ocena',''))>2:
  517.       outree['Komentarz']=outree.setdefault('Komentarz','')+outree['Ocena']
  518.       outree['Ocena']='T'
  519.     if parser.tree.childNodes[0].nodeName!='nauczyciel':
  520.       print "#err brak zapytaj_nauczyciela in %s"%fn
  521.       return NotImplemented
  522.     outree['nauczyciel_id']=int(parser.tree.childNodes[0].innerHTML)
  523.     myfn=fn[:fn.rfind('.')]
  524.     outree['ocena_id']=int(myfn.split('/')[-1])
  525.     try:
  526.       if glob.glob(myfn.replace('oceny_szczegoly','oceny_export/new')+'*') or glob.glob(myfn.replace('oceny_szczegoly','oceny_export/cur')+'*'):
  527.       pass
  528.       else:
  529.       with open(myfn.replace('oceny_szczegoly','oceny_export/new'),'w') as fp82:
  530.           fp82.write('Subject: %s'%safemakeheaderu8('%s: %s'%(outree['Przedmiot'],outree['Ocena'])))
  531.           fp82.write('''
  532. Content-Type: text/html; charset="utf-8"
  533. Content-Transfer-Encoding: quoted-printable
  534. Date: %s
  535. '''%(time.strftime(rfc822fmt, time.strptime(outree['Data'][:outree['Data'].find(' ')],librfmt))))
  536.           # FIXME: nauczyciel_id = id(nauczyciel); id(dodał)=?
  537.           head='%s <%s@%s>'%(safemakeheaderu8(outree['Dodał'.decode('utf')],'"'),outree['nauczyciel_id'],host)
  538.           fp82.write('From: %s'%head)
  539.           fp82.write('''
  540. MIME-Version: 1.0
  541.  
  542. ''')
  543.           x=wrap_HTML(tree.innerHTML.encode('utf')).encode('quoted-printable')
  544.           print (x)
  545.           fp82.write(x)
  546.     except KeyError,e:
  547.       print 'Smutne strasznie ;(',e,myfn,outree
  548.       os.remove(myfn.replace('oceny_szczegoly','oceny_export/new'))
  549.     #oceny[outree['Przedmiot']][0].append(outree)
  550.     return outree
  551.  
  552. def update_graph():
  553.     #href='/uczen/graph_ajax.php?type=wykres_sredniej&classId=37253&userId=918577'
  554.     href='/uczen/graph_ajax.php?type=wykres_sredniej&classId=50832&userId=1261841'
  555.     global fn,url
  556.     oldfn,fn=fn,'graph.html'
  557.     url = site + href
  558.     update()
  559.     print (parse3())
  560.     fn=oldfn
  561.  
  562. def main():
  563.     global url
  564.     jar.set_cookie(cookielib.Cookie(0, 'TestCookie', '1',
  565.             None, False,
  566.             host, True, False,
  567.             '/', False,
  568.             False,
  569.             None,
  570.             False,
  571.             None,
  572.             None,
  573.             {}))
  574.     if os.path.isfile(cookiefn):
  575.     jar.load(ignore_discard=True)
  576.     if not os.path.isfile(fn):
  577.     update()
  578.     parse()
  579.     for an_id in oceny_ids:
  580.     if int(an_id[an_id.rfind('/')+1:])==0: continue
  581.     x=get_details(an_id)
  582.     if x not in baza:
  583.         baza.append(x)
  584.         #with open('bazaocen.py','w') as fp99:
  585.         #fp99.write('baza=%r\n'%baza)
  586.     with open('db/gradonly_auto.sql','w') as fp137:
  587.     mapa=[(entry['ocena_id'],entry['Ocena'],entry['Kategoria'].replace("'","''"),entry['Data'][:10],
  588.   entry['nauczyciel_id'],entry['Przedmiot'],'1' if entry.get('Licz do średniej') else '0',
  589.   entry.get('Waga','1'),dodal(entry)[0],dodal(entry)[1],entry.get('Komentarz','').replace("'","''")) for entry in baza]
  590.     fp137.write((u'''INSERT OR REPLACE INTO oceny (
  591.  ocena_id, ocena, kategoria, data_dodania, nauczyciel, przedmiot, licz_do_sr, waga, dodal, komentarz
  592. ) VALUES (''' + u'),('.join([u'''
  593.  %s, '%s', '%s', '%s', %s, (SELECT przedmiot_id FROM przedmioty WHERE nazwa='%s'), %s, %s, (SELECT uzytkownik_id FROM uzytkownicy WHERE imie='%s' AND nazwisko='%s'), '%s'
  594. '''%x for x in mapa])+
  595. ''');
  596. ''').encode('utf'))
  597.     update_graph()
  598.     with open(os.path.splitext(fn)[0]+".json",'wb') as fp:
  599.     fp.write(repr(oceny).replace(',',',\n')
  600.       .replace('[','[\n ').replace(']','\n]')
  601.       .replace("'",'"').replace("\n ","\n  ")
  602.       .replace('],\n  ','],\n ').replace(']',' ]')
  603.       .replace('{','{\n ').replace('}','\n}')
  604.     )
  605.     jar.save(ignore_discard=True)
  606.  
  607. if __name__=="__main__":
  608.     x=os.path.dirname(sys.argv[0])
  609.     if x: os.chdir(x)
  610.     interact = False
  611.     try:
  612.       main()
  613.     except:
  614.       traceback.print_exc()
  615.       interact = True
  616.     if interact:
  617.       filename = os.environ.get('PYTHONSTARTUP')
  618.       if filename and os.path.isfile(filename):
  619.       with open(filename) as fobj:
  620.           startup_file = fobj.read()
  621.       exec(startup_file)
  622.       code.interact(local=globals())
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!