Habrタグの人気：投稿の傾向は？

  def get_tag(self, name, added = True): """  ,    tid,    cur -   res -        added - /     ,     false """ cur=self.con.execute("select rowid from %s where %s='%s'" % ('tags','tag_title',name)) res=cur.fetchone( ) if res==None: if added: cur=self.con.execute("insert into %s (%s) values ('%s')" % ('tags','tag_title',name)) self.con.commit( ) return cur.lastrowid else: return False else: return res[0] def add_tag(self, pid, name, date): """    pid -   name -   date -   """ rowid = self.get_tag(name); print(pid,rowid ,name, date) self.con.execute("insert into %s (%s,%s,%s) values (%d,%d,'%s')" % ('post_tags','pid','tid','date',pid,rowid,date)) self.con.commit( ) def add_post(self, pid): """   (   ) """ if (self.get_post(pid)): return print('-'*10,'http://habrahabr.ru/post/'+str(pid),'-'*10) cur=self.con.execute("select pid from %s where %s=%d" % ('post_tags','pid',pid)) res=cur.fetchone( ) if res==None: try: soup=BeautifulSoup(urllib.request.urlopen('http://habrahabr.ru/post/'+str(pid)).read( )) except (urllib.request.HTTPError): self.add_tag(pid,"parse_error_404","") print("error 404") else: published = soup.find("div", { "class" : "published" }) tags = soup.find("ul", { "class" : "tags" }) if tags: for tag in tags.findAll("a"): self.add_tag(pid, tag.string, get_date(published.string)) else: self.add_tag(pid,"parse_access_denied","") print("access denied") else: print("post has already") 

  def get_count_byname(self, name, date = ''): """  name  tid       get_count_byid name -   date - (*)  mm_yyyy """ tid = self.get_tag(name, False) return self.get_count_byid(tid, date) def get_count_byid(self, tid, date = ''): """          """ if tid: if date: count=self.con.execute("select count(pid) from %s where %s=%d and %s='%s'" % ('post_tags','tid',tid,'date',date)) else: count=self.con.execute("select count(pid) from %s where %s=%d" % ('post_tags','tid',tid)) res=count.fetchone( ) return res[0] else: return False def get_graph(self, name): """    -  """ month = ('01',''),('02',''),('03',''),('04',''),('05',''),('06',''),('07',''),('08',''),('09',''),('10',''),('11',''),('12','') years = [2006,2007,2008,2009,2010,2011,2012,2013] graph = [] for Y in years: for M,M_str in month: date = str(M)+'_'+str(Y) graph.append((date, self.get_count_byname(name, date))) return graph def get_image(self, name): """   m_x -   X m_y -   Y img_x -   img_y -   """ img_x = 960 img_y = 600 img=Image.new('RGB',(img_x,img_y),(255,255,255)) draw=ImageDraw.Draw(img) graph = self.get_graph(name) max_y = max(graph,key=lambda item:item[1])[1] if max_y == 0: print('tag not found') return False m_x, m_y = int(img_x/(len(graph))), int(img_y/max_y) draw.text((10, 10), str(max_y), (0,0,0)) draw.text((10, 20), name, (0,0,0)) x,prev_y = 0,-1 for x_str, y in graph: x += 1 if (x%12 == 1): draw.text((x*m_x, img_y - 30), str(x_str[3:]),(0,0,0)) if prev_y >= 0: draw.line(((x-1)*m_x, img_y-prev_y*m_y-1, x*m_x, img_y-y*m_y-1), fill=(255,0,0)) prev_y = y img.save('graph.png','PNG') Image.open('graph.png').show() def get_all_tags_sorted(self, tags): """   """ return sorted(tags, key=lambda tag:tag[2], reverse=True) def get_all_tag_count(self): count=self.con.execute("select count(rowid) from %s" % ('tags')) res=count.fetchone( ) alltag_count = res[0] tags = [] for tag_id in range(alltag_count-1): tags.append((tag_id+1,self.get_tag_name(tag_id+1),self.get_count_byid(tag_id+1))) print (tag_id+1,self.get_tag_name(tag_id+1),self.get_count_byid(tag_id+1)) return tags