Diaro App : DiaroBackup.xml : How to parse in python ? (Draft n°2)

(See the finale release : https://www.cyber-neurones.org/2019/02/diaro-app-pixel-crater-ltd-diarobackup-xml-how-to-migrate-data-to-joplin/ )

I have issue with ressources (link between ressources and notes) …. error 404. The logs in : .config/joplin-desktop/log-clipper.txt

....: "Request: PUT /ressources/71dd2cba2af54c4ebb53fb7fd8d0543b/notes/cbbc6076b2ac321ccae1f036a2fe6659?token=...."
....: "Error: Not Found
Error: Not Found
    at Api.route (/Applications/Joplin.app/Contents/Resources/app/lib/services/rest/Api.js:103:41)
    at execRequest (/Applications/Joplin.app/Contents/Resources/app/lib/ClipperServer.js:147:39)
    at IncomingMessage.request.on (/Applications/Joplin.app/Contents/Resources/app/lib/ClipperServer.js:185:8)
    at emitNone (events.js:105:13)
    at IncomingMessage.emit (events.js:207:7)
    at endReadableNT (_stream_readable.js:1045:12)
    at _combinedTickCallback (internal/process/next_tick.js:138:11)
    at process._tickCallback (internal/process/next_tick.js:180:9)"

My last code :

#
# Version 2 
# for Python 3
# 
#   ARIAS Frederic
#   Sorry ... It's difficult for me the python :)
#

#from lxml import etree
import xml.etree.ElementTree as etree
from time import gmtime, strftime
import time
import json
import requests
import os

strftime("%Y-%m-%d %H:%M:%S", gmtime())
start = time.time()

#Token
ip = "127.0.0.1"
port = "41184"
token = "ABCD123ABCD123ABCD123ABCD123ABCD123"

url_notes = (
    "http://"+ip+":"+port+"/notes?"
    "token="+token
)
url_folders = (
    "http://"+ip+":"+port+"/folders?"
    "token="+token
)
url_tags = (
    "http://"+ip+":"+port+"/tags?"
    "token="+token
)
url_ressources = (
    "http://"+ip+":"+port+"/ressources?"
    "token="+token
)

#Init
Diaro_UID = "12345678901234567801234567890123"
Lat = {}
Lng = {}
UID = {} 
TAGS = {}
Lat[""] = ""
Lng[""] = ""

payload = {
    "id": Diaro_UID,
    "title": "Diaro Import"
}

try:
    resp = requests.post(url_folders, json=payload)
    #time.sleep(1)
    resp.raise_for_status()
    resp_dict = resp.json()
    print(resp_dict)
    print("My ID")
    print(resp_dict['id'])
    Diaro_UID_real = resp_dict['id']
    save = str(resp_dict['id'])
    UID[Diaro_UID]= save
except requests.exceptions.HTTPError as e:
    print("Bad HTTP status code:", e)
except requests.exceptions.RequestException as e:
    print("Network error:", e)

print("Start : Parse Table")
tree = etree.parse("./DiaroBackup.xml")
for table in tree.iter('table'):
    name = table.attrib.get('name')
    print(name)
    myorder = 1
    for r in table.iter('r'):
         myuid = ""
         mytitle = ""
         mylat = ""
         mylng = ""
         mytags = ""
         mydate = ""
         mydate_ms = 0;
         mytext = ""
         myfilename = ""
         myfolder_uid = Diaro_UID
         mylocation_uid = ""
         myprimary_photo_uid = ""
         myentry_uid = ""
         myorder += 1
         for subelem in r:
             print(subelem.tag)
             if (subelem.tag == 'uid'):
                 myuid = subelem.text
                 print ("myuid",myuid)
             if (subelem.tag == 'entry_uid'):
                 myentry_uid = subelem.text
                 print ("myentry_uid",myentry_uid)
             if (subelem.tag == 'primary_photo_uid'):
                 myprimary_photo_uid = subelem.text
                 print ("myprimary_photo_uid",myprimary_photo_uid)
             if (subelem.tag == 'folder_uid'):
                 myfolder_uid = subelem.text
                 print ("myfolder_uid",myfolder_uid)
             if (subelem.tag == 'location_uid'):
                 mylocation_uid = subelem.text
                 print ("mylocation_uid",mylocation_uid)
             if (subelem.tag == 'date'):
                 mydate = subelem.text
                 mydate_ms = int(mydate)
                 print ("mydate",mydate," in ms",mydate_ms)
             if (subelem.tag == 'title'):
                 mytitle = subelem.text
                 print ("mytitle",mytitle)
                 #if type(mytitle) == str:
                    #mytitle = mytitle.encode('utf8')
             if (subelem.tag == 'lat'):
                 mylat = subelem.text
                 print ("mylat",mylat)
             if (subelem.tag == 'lng'):
                 mylng = subelem.text
                 print ("mylng",mylng)
             if (subelem.tag == 'tags'):
                 mytags = subelem.text
                 if mytags:
                    mytags[1:]
                 print ("mytags",mytags)
             if (subelem.tag == 'text'):
                 mytext = subelem.text
                 print ("mytext",mytext)
                 #if type(mytext) == str:
                       #mytext = mytext.encode('utf8')
             if (subelem.tag == 'filename'):
                 myfilename = subelem.text
                 print ("myfilename",myfilename)
                 
         if (name == 'diaro_folders'):
            payload_folder = {
  "id": myuid,
  "title": mytitle,
  "parent_id": Diaro_UID_real
}
            print(payload_folder)
            try:
                resp = requests.post(url_folders, json=payload_folder)
                #time.sleep(1)
                resp.raise_for_status()
                resp_dict = resp.json()
                print(resp_dict)
                print(resp_dict['id'])
                save = str(resp_dict['id']) 
                UID[myuid]= save
            except requests.exceptions.HTTPError as e:
                print("Bad HTTP status code:", e)
            except requests.exceptions.RequestException as e:
                print("Network error:", e)

         if (name == 'diaro_tags'):
            payload_tags = {
                "id": myuid,
                "title": mytitle
            }
            try:
                resp = requests.post(url_tags, json=payload_tags)
                #time.sleep(1)
                resp.raise_for_status()
                resp_dict = resp.json()
                print(resp_dict)
                print(resp_dict['id'])
                UID[myuid]= resp_dict['id']
                TAGS[myuid] = mytitle
            except requests.exceptions.HTTPError as e:
                print("Bad HTTP status code:", e)
            except requests.exceptions.RequestException as e:
                print("Network error:", e)

         if (name == 'diaro_attachments'):
            payload_ressource = {
                "id": myuid
            }
            filename = "./media/photo/"+myfilename
            files = {'document': open(filename, 'rb')}
            files2 = {'data': open(filename, 'rb')}
            files3 = {'data': open(filename, 'rb'), 'props': payload_ressource}
            data_ressource = {
                 "title": myfilename
            }
            multiple_files = [
                ('data', (myfilename, open(filename, 'rb'))),
                ('props', data_ressource)]
            headers = {'Content-type': 'multipart/form-data'}
            print("Push : "+filename);
            #print os.path.isfile(filename)
            print("----------0-----------")
            #try:
               #resp = requests.post(url_ressources, files=filename, json=payload_ressource)
               #resp = requests.post(url_ressources, files=files, json=payload_ressource, headers=headers) 
               #resp = requests.post(url_ressources, files=files2, headers=headers)
               #resp = requests.post(url_ressources, files=files2, headers=headers)
               #resp = requests.post(url_ressources,files = {'data' : (myfilename, open(filename, 'rb'), 'image/jpg')}, data = {'id' : myuid}, headers=headers)
               #resp = requests.post(url_ressources,files = files2, data= data_ressource, headers=headers)
               #resp = requests.post(url_ressources,files = multiple_files, headers=headers)
               #resp = requests.post(url_ressources,files = multiple_files)
               #resp.text
               #time.sleep(1)
               #resp.raise_for_status()
               #if (resp.status_code == requests.codes.ok):
               #    resp_dict = resp.json()
               #    print(resp_dict)
               #    print(resp_dict['id'])
               #    UID[myuid]= resp_dict['id']
            #except requests.exceptions.HTTPError as e:
               #print("Bad HTTP status code:", e)
               #UID[myuid]=""
               #print("----------1-----------")
            #except requests.exceptions.RequestException as e:
               #print("Network error:", e)
               #UID[myuid]=""
               #print("----------2-----------")

            cmd = "curl -F 'data=@"+filename+"' -F 'props={\"title\":\""+myfilename+"\"}' http://"+ip+":"+port+"/resources?token="+token
            resp = os.popen(cmd).read()
            respj = json.loads(resp)
            #resp_dict = respj.json() 
            print(respj['id'])
            UID[myuid]= respj['id']

            print("Link : ",myuid," => ",myentry_uid," // ",UID[myuid]+" => ",UID[myentry_uid])
            time.sleep(1)

            cmd = "curl -X PUT http://"+ip+":"+port+"/ressources/"+UID[myuid]+"/notes/"+UID[myentry_uid]+"?token="+token
            resp = os.popen(cmd).read()
            print (resp)
            #url_link = (
            #   "http://"+ip+":"+port+"/ressources/"+UID[myuid]+"/notes/"+UID[myentry_uid]+"?"
            #   "token="+token
            #   )
            #try:
            #  resp = requests.post(url_link)
            #   #time.sleep(1)
            #   resp.raise_for_status()
            #   resp_dict = resp.json()
            #   print(resp_dict)
            #   print(resp_dict['id'])
            #   UID[myuid]= resp_dict['id']
            #except requests.exceptions.HTTPError as e:
            #   print("Bad HTTP status code:", e)
            #except requests.exceptions.RequestException as e:
            #   print("Network error:", e)

         if (name == 'diaro_locations'):
              Lat[myuid] = mylat
              Lng[myuid] = mylng

         if (name == 'diaro_entries'):
            if not mytext:
                  mytext = ""
            if not myfolder_uid:
                  myfolder_uid = Diaro_UID
            if not mytags:
                  mytags = ""
            if not mylocation_uid:
                  mylocation_uid = ""
            mytext = mytext.replace("'", "")
            mytitle = mytitle.replace("'", "")
            mytext = mytext.strip("\'")
            mytitle = mytitle.strip("\'")
            mytext = mytext.strip('(')
            mytitle = mytitle.strip('(')
            listtags = mytags.split(",")
            new_tagslist = "";
            for uid_tags in listtags:
                 if (len(uid_tags) > 2):
                        if uid_tags in UID:
                             new_tagslist = new_tagslist + TAGS[uid_tags] + ",";
            print ("TAGS",mytags,"==>",new_tagslist);
            payload_note = {
                "id": myuid,
                "latitude": Lat[mylocation_uid],
                "longitude": Lng[mylocation_uid],
                "tags": new_tagslist,
                "parent_id": UID[myfolder_uid],
                "title": mytitle,
                #"created_time": mydate_ms,
                "user_created_time": mydate_ms,
                "user_updated_time": mydate_ms,
                "author": "Diaro",
                "body": mytext 
            }
            try:
                resp = requests.post(url_notes, json=payload_note)
                #time.sleep(1)
                resp.raise_for_status()
                resp_dict = resp.json()
                print(resp_dict)
                print(resp_dict['id'])
                UID[myuid]= resp_dict['id']
            except requests.exceptions.HTTPError as e:
                print("Bad HTTP status code:", e)
            except requests.exceptions.RequestException as e:
                print("Network error:", e)

print("End : Parse Table")

strftime("%Y-%m-%d %H:%M:%S", gmtime())
done = time.time()
elapsed = done - start
print(elapsed)

# END : Ouf ...

Laisser un commentaire

Votre adresse e-mail ne sera pas publiée. Les champs obligatoires sont indiqués avec *

Time limit is exhausted. Please reload CAPTCHA.