API tools faq
paste
Advertisement
Guest User

ImportmangalistfromAPtoMAL

a guest
Apr 12th, 2017
90
1
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Python 11.60 KB | None | 1 0
raw download clone embed print report
  1. #!/usr/bin/python
  2. #This script will take your manga-planet.com username and add your list to MAL using its API
  3. #Errors are output so you can enter those manually
  4. #set debug = True to get more information on all of your entries
  5. #Additional info and packages:
  6. #  Python 3.3.3 - http://python.org/download/
  7. #  BeautifulSoup4 - http://www.crummy.com/software/BeautifulSoup/#Download
  8. #Tips:
  9. # * You can leave your MAL username empty if it's the same as on mangaPlanet.
  10. # * To install BeautifulSoup unpack it anywhere and type "setup.py install" in the console from that folder.
  11. # * In order to successfully import the exported anime-Planet mangalist to MAL, first export MAL mangalist,
  12. #    and copy the <myinfo> block just after <myanimelist> tag.
  13.  
  14. from bs4 import BeautifulSoup,NavigableString
  15. import urllib.request,urllib.parse,base64,sys,re,codecs
  16. import xml.etree.ElementTree as et
  17.  
  18. debug = False
  19. delimiter = "\t"
  20. userAgent = "Mozilla/5.0 (Windows NT 6.2; Win64; x64;) Gecko/20100101 Firefox/20.0"
  21.  
  22. print("This script will export your anime-planet.com anime list to myanimelist.net")
  23.  
  24. username = input("Enter your AP username:")
  25. malusername = input("Enter your MAL username:")
  26. if (malusername == ""): malusername = username
  27. malpassword = input("Enter your MAL password:")
  28.  
  29. baseURL = "http://www.anime-planet.com/users/%s/manga" %username
  30. apiURL = "https://myanimelist.net/api/manga/search.xml"
  31. apiURLadd = "https://myanimelist.net/api/mangalist/add/%s.xml"
  32. apiURLupdate = "https://myanimelist.net/api/mangalist/update/%s.xml"
  33.  
  34. passStr = str("%s:%s" % (malusername, malpassword)).replace("\n", "")
  35. authString = str(base64.b64encode(bytes(passStr, "utf-8")), "utf-8")
  36. if debug: print("MAL authorization hash:" + authString)
  37.  
  38. #Try to get HTML of first page.
  39. try:
  40.     req = urllib.request.Request(baseURL)
  41.     req.add_header("User-Agent",  userAgent)
  42.     html = BeautifulSoup(urllib.request.urlopen(req).read(), "html.parser")
  43.     pageNumber = int (html.find("li","next").findPrevious("li").next.contents[0])
  44.     #if your list is only one page, uncomment the line below and comment the line above
  45.     #pageNumber = int (html.find('li','next').findPrevious('li').contents[0])
  46. except BaseException as e:
  47.     print("Request to " + baseURL + " failed. " +str(e))
  48.     raise SystemExit
  49.  
  50. print("Processing AP list and requesting data from MAL...")
  51.  
  52. #loop through all of your pages
  53. for i in range(1,pageNumber+1):
  54.     try:
  55.         req = urllib.request.Request(baseURL + "?" + urllib.parse.urlencode({"page": str(i)}))
  56.         if debug: print("Calling URL:" + baseURL + "?" + urllib.parse.urlencode({"page": str(i)}))
  57.         req.add_header("User-Agent",  userAgent)
  58.         html = BeautifulSoup(urllib.request.urlopen(req).read(), "html.parser")
  59.     except BaseException as e:
  60.             print("Request to " + baseURL + "?" + urllib.parse.urlencode({"page": str(i)}) + " failed. " +str(e))
  61.             raise SystemExit
  62.     #loop through all of the manga posters on page i
  63.     for mangaItem in html.findAll("li",class_="card"):
  64.         mangaItem = BeautifulSoup(mangaItem.renderContents(), "html.parser")
  65.         mangaName = "" + mangaItem.a.div.img["alt"]
  66.         #pretty apostophe was breaking things
  67.         mangaName = mangaName.replace("'","'")
  68.         queryTitle = ""
  69.         try:
  70.             titlereq = urllib.request.Request(apiURL + "?" + urllib.parse.urlencode({ "q" : mangaName }))
  71.             titlereq.add_header("Authorization", "Basic %s" % authString)
  72.             titlereq.add_header("User-Agent",  userAgent)
  73.             queryTitle = urllib.request.urlopen(titlereq).read().decode("utf-8")
  74.             #I think this removes the synopsis for some reason, whatever
  75.             queryTitle = re.sub(r"(?is)<synopsis>.+</synopsis>", "", queryTitle)
  76.         except BaseException as e:
  77.             print("manga: " + mangaName)
  78.             print("Request to " + apiURL + "?" + urllib.parse.urlencode({ "q" : mangaName }) + " failed. " +str(e))
  79.             raise SystemExit
  80.         #get the status, which is now a class name
  81.         status = mangaItem.find("div","statusArea").span["class"][0]
  82.         formattedStatus = ""
  83.         if status=="status6":
  84.             formattedStatus = "won't read"
  85.             status="4"
  86.         elif status=="status3":
  87.             formattedStatus = "dropped"
  88.             status="4"
  89.         elif status=="status4":
  90.             formattedStatus = "want to read"
  91.             status="6"
  92.         elif status=="status5":
  93.             formattedStatus = "stalled"
  94.             status="3"
  95.         elif status=="status1":
  96.             formattedStatus = "read"
  97.             status="2"
  98.         elif status=="status2":
  99.             formattedStatus = "reading"
  100.             status="1"
  101.         search = ""
  102.         try:
  103.             if queryTitle != '':
  104.                 search = et.fromstring(queryTitle)
  105.                 if debug: print("================")
  106.                 if debug: print("manga: " + mangaName)
  107.                 if debug: print(apiURL + "?" + urllib.parse.urlencode({ "q" : mangaName }))
  108.             else:
  109.                 # This item failed to get a title match
  110.                 if ":" not in mangaName:
  111.                     print("================")
  112.                     print("manga: " + mangaName)
  113.                     print(apiURL + "?" + urllib.parse.urlencode({ "q" : mangaName }))
  114.                     print("Search failed; no match found.")
  115.                     print("Status: " + formattedStatus)
  116.                     continue
  117.                 else:
  118.                     #try truncated name for initial search
  119.                     formattedName = mangaName.split(":")[0]
  120.                     try:
  121.                         titlereq = urllib.request.Request(apiURL + "?" + urllib.parse.urlencode({ "q" : formattedName }))
  122.                         titlereq.add_header("Authorization", "Basic %s" % authString)
  123.                         titlereq.add_header("User-Agent",  userAgent)
  124.                         queryTitle = urllib.request.urlopen(titlereq).read().decode("utf-8")
  125.                         #I think this removes the synopsis for some reason, whatever
  126.                         queryTitle = re.sub(r"(?is)<synopsis>.+</synopsis>", "", queryTitle)
  127.                     except BaseException as e:
  128.                         print("manga: " + mangaName)
  129.                         print("Request to " + apiURL + "?" + urllib.parse.urlencode({ "q" : formattedName }) + " failed. " +str(e))
  130.                         raise SystemExit
  131.                     if queryTitle != '':
  132.                         search = et.fromstring(queryTitle)
  133.                         if debug: print("================")
  134.                         if debug: print("manga: " + mangaName)
  135.                         if debug: print(apiURL + "?" + urllib.parse.urlencode({ "q" : formattedName }))
  136.                     else:
  137.                         # This item failed to get a title match
  138.                         print("================")
  139.                         print("manga: " + mangaName)
  140.                         print(apiURL + "?" + urllib.parse.urlencode({ "q" : formattedName }))
  141.                         print("Search failed; no match found.")
  142.                         print("Status: " + formattedStatus)
  143.                         continue
  144.                 continue
  145.         except BaseException as e:
  146.             print("Decoding of manga data failed. Error: " +str(e))
  147.             # for adding manga manually
  148.             continue
  149.         localName = mangaName.lower().replace(":","").replace("(","").replace(")","")
  150.         mangaID = ""
  151.         chapterCount = ""
  152.         #check all results for an id
  153.         for entry in search.findall("./entry"):
  154.             try:
  155.                 if entry.find("id") is not None and entry.find("id").text.strip()!="":
  156.                     if entry.find("title") is not None and localName in entry.find("title").text.lower().replace(":","").replace("(","").replace(")",""):
  157.                         mangaID=entry.find("id").text
  158.                         chapterCount = entry.find("chapters").text
  159.                         break
  160.                     elif entry.find("english") is not None and localName in entry.find("english").text.lower().replace(":","").replace("(","").replace(")",""):
  161.                         mangaID=entry.find("id").text
  162.                         chapterCount = entry.find("chapters").text
  163.                         break
  164.                     elif entry.find("synonyms") is not None and localName in entry.find("synonyms").text.lower().replace(":","").replace("(","").replace(")",""):
  165.                         mangaID=entry.find("id").text
  166.                         chapterCount = entry.find("chapters").text
  167.                         break
  168.             except:
  169.                 continue
  170.         if mangaID=="":
  171.             print("No MAL ID found in returned results.")
  172.             continue
  173.         if debug: print("MAL ID = " + mangaID)
  174.  
  175.         xmlData = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n"
  176.         xmlData += "<entry>\n"
  177.  
  178.         if status == "4" or status == "6":
  179.             xmlData += "\t<chapter></chapter>\n"
  180.         #had to include read here because there's no way to get the # of ch anymore from AP
  181.         elif status == "2":
  182.             xmlData += "\t<chapter>" + chapterCount + "</chapter>\n"
  183.         else:
  184.             xmlData += "\t<chapter>"+ mangaItem.find("div","statusArea").text.replace("ch","").replace("vol","").replace("\t", "").replace("\n", "").replace("\r", "").replace(" ", "") +"</chapter>\n"
  185.         xmlData += "\t<status>" + status +"</status>\n"
  186.         try:
  187.             rating = mangaItem.find("div", attrs={"class": "ttRating"}).text;
  188.             xmlData += "\t<score>" + str(int(float(rating)*2)) + "</score>\n"
  189.         except:
  190.             xmlData += "\t<score></score>\n"
  191.            
  192.         xmlData += "\t<downloaded_chapters></downloaded_chapters>\n"
  193.         xmlData += "\t<storage_type></storage_type>\n"
  194.         xmlData += "\t<storage_value></storage_value>\n"
  195.         xmlData += "\t<times_reread></times_reread>\n"
  196.         xmlData += "\t<reread_value></reread_value>\n"
  197.         xmlData += "\t<date_start></date_start>\n"
  198.         xmlData += "\t<date_finish></date_finish>\n"
  199.         xmlData += "\t<priority></priority>\n"
  200.         xmlData += "\t<enable_discussion></enable_discussion>\n"
  201.         xmlData += "\t<enable_rereading></enable_rereading>\n"
  202.         xmlData += "\t<comments></comments>\n"
  203.         xmlData += "\t<fansub_group></fansub_group>\n"
  204.         xmlData += "\t<tags></tags>\n"
  205.         xmlData += "</entry>\n"
  206.  
  207.         params = {'id' : mangaID, 'data' : xmlData}
  208.         isAdded = False
  209.         try:
  210.             if debug:
  211.                 print("Trying to add manga... ")
  212.             url = urllib.request.Request(apiURLadd % mangaID, urllib.parse.urlencode(params).encode("utf-8"))
  213.             url.add_header("Authorization", "Basic %s" % authString)
  214.             url.add_header("User-Agent",  userAgent)
  215.             urllib.request.urlopen(url)
  216.             isAdded = True
  217.         except:
  218.             isAdded = False
  219.         if not isAdded:
  220.             try:
  221.                 if debug:
  222.                     print("\rTrying to update manga... ")
  223.                 url = urllib.request.Request(apiURLupdate % mangaID, urllib.parse.urlencode(params).encode("utf-8"))
  224.                 url.add_header("Authorization", "Basic %s" % authString)
  225.                 url.add_header("User-Agent",  userAgent)
  226.                 urllib.request.urlopen(url)
  227.                 isAdded = True
  228.             except:
  229.                 isAdded = False
  230.         if debug:
  231.             if isAdded: sys.stdout.write("OK\n")
  232.             else: sys.stdout.write("FAILED\n")
  233.             sys.stdout.flush()
  234.  
  235. print("\nDone")
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!