def mangdl(self): try: mangaLinkMap = pickle.load(open("dbase.txt", 'r')) #Go to the main page of the manga title #and Download the first chapter. Trial. #But, before that, create a new folder dedicated to this #particular manga title and aslo a folder for chapter 1 print "Ore ha koko ni iru" x = namelist[self.val] remove_set.add(x+'.html') if not os.path.isfile(x + '.html'): urllibX.urlretrieve('http://www.mangareader.net'\ +mangaLinkMap[x], x+'.html') print 'Node boku mo ', mangaLinkMap[x] print "Soshite, sono namae ha ", x newDict = chapMap(x+'.html') clickable_wind(newDict, x) except: pass
def chapDL(index, listChap, mangaName): print listChap[index], " -<-< Doitsumo Koitsumo" urlH = chapDict[listChap[index]] print "url ha ", urlH print "Manganame ha ", mangaName apos = "\'" apos+mangaName+apos+" "+ apos+listChap[index]+apos os.system("./folcreate.sh "+ apos+mangaName+apos+" "+apos+listChap[index]+apos) fileS = './'+mangaName+'/'+listChap[index]+ '/'+listChap[index]+'.html' namelist = [] first = int(sys.argv[1]) PAGES = int(sys.argv[2]) # Checks for PAGES pages for i in range(first, PAGES): #Differentiates between old-type and new-type links if '-' in urlH and is_int(urlH[urlH.index('-')+1]): print "LINKTYPE: Old" ind = find_nth(urlH, '-', 2) copy = urlH digiLen = 2 copy = copy[:ind+1] + str(i) +'/' +copy[ind+len(str(i))+digiLen:] print "OURLINK: ", copy urllibX.urlretrieve("http://www.mangareader.net"+copy, fileS) else: urllibX.urlretrieve("http://www.mangareader.net"+urlH+'/'+str(i), fileS) #Open the chapter page imgSoup = bs4.BeautifulSoup(open(fileS, 'r')) chitra = imgSoup.findAll('img') #Display the source img for each in chitra: print "LINK" print each['src'] link = each['src'] #Get the filename-after the last / name = link[link.rfind('/')+1:len(link)] namelist.append(name) urllibX.urlretrieve(link, mangaName+'/'+listChap[index]+'/'+name) '''
#import re, sys, urllib, os import re, sys, urllibX, os import shutil # modified urllib (user-agent string change) fi = open(sys.argv[1]).read() matches = re.search('img src="([^"]+)"', fi).group() a = matches[9:-1] b = urllibX.urlretrieve(a) try: os.rename(b[0], sys.argv[3] + sys.argv[2] + ".jpg") except: shutil.move(b[0], sys.argv[3] + sys.argv[2] + ".jpg")
print "STAGE 3" for chapter in lC: temp = Checkbutton(root2, text=chapter, variable=choice[chapter]) text.window_create("end", window=temp) text.insert("end", "\n") # in order to force one checkbox per line button = Button(root2, text='Download Chapter(s)',command= lambda:chapVal(mangaName, lC, choice)) button.pack() #root2.mainloop() print "TEME!!!!!!! ", val #Make list of manga titles if not os.path.isfile("mnrdl_list.html"): urllibX.urlretrieve("http://www.mangareader.net/alphabetical",\ "mnrdl_list.html") myDict = {} if not os.path.isfile("dbase.txt"): soup = bs4.BeautifulSoup(open('mnrdl_list.html')) f1 = open('dbase.txt', 'w+') mname = soup.findAll('a') for node in mname: a = ''.join(node.findAll(text=True)) b = None if node.attrs.has_key('href'): b = node['href'] myDict[a] = b pickle.dump(myDict, f1) f1.close()