Add genxmp.py

genxmp.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python3
+from html.parser import HTMLParser
+import xml.etree.ElementTree as ET
+from xml.dom import minidom
+from pathlib import Path
+import json
+import re
+import os
+
+class HTMLFilter(HTMLParser):
+    text = ""
+    def handle_data(self, data):
+        self.text += data + "\n"
+
+def get_data(type, path):
+  with open(path) as file:
+    data = json.load(file)
+
+  desc = ""
+  tags = []
+  date = data["date"]
+
+  if type == "bluesky":
+    desc = data["text"]
+  elif type == "twitter":
+    desc = data["content"]
+  elif type == "furaffinity":
+    desc = data["title"] + "\n\n" + data["description"]
+    tags = data["tags"]
+    if tags:
+      tags.reverse()
+      tags.pop()
+      tags.reverse()
+  elif type == "pixiv":
+    f = HTMLFilter()
+    f.feed(data["caption"])
+    desc = data["title"] + "\n\n" + f.text
+    tags = data["tags"]
+    date += "." + str(data["num"])
+
+  if type == "bluesky" or type == "twitter":
+    tags = re.findall(r"#(\w+)", desc)
+
+  return desc, tags, date
+
+count = 0
+for path in Path("media").rglob("*.json"):
+  file = os.path.splitext(path)[0] + ".xmp"
+  if os.path.exists(file):
+    continue
+
+  type = str(path).split("/")[1]
+
+  desc, tags, date = get_data(type, path)
+
+  root = minidom.Document()
+  xml = root.createElement("x:xmpmeta")
+  xml.setAttribute("xmlns:x", "adobe:ns:meta/")
+  xml.setAttribute("x:xmptk", "genxmp.py")
+  root.appendChild(xml)
+
+  rdf = root.createElement("rdf:RDF")
+  rdf.setAttribute("xmlns:rdf", "http://www.w3.org/1999/02/22-rdf-syntax-ns#")
+  rdfDesc = root.createElement("rdf:Description")
+  rdfDesc.setAttribute("rdf:about", "")
+
+  descr = root.createElement("dc:description")
+  descr.appendChild(root.createTextNode(desc))
+  rdfDesc.appendChild(descr)
+
+  exifdate = root.createElement("exif:DateTimeOriginal")
+  exifdate.appendChild(root.createTextNode(date))
+  rdfDesc.appendChild(exifdate)
+
+  namespaces = {
+    "digiKam": "http://www.digikam.org/ns/1.0/",
+    "MicrosoftPhoto": "http://ns.microsoft.com/photo/1.0",
+    "lr": "http://ns.adobe.com/lightroom/1.0/",
+    "mediapro": "http://ns.iview-multimedia.com/mediapro/1.0/",
+    "acdsee": "http://ns.acdsee.com/iptc/1.0/",
+    "dc": "http://purl.org/dc/elements/1.1/",
+    "xmp": "http://ns.adobe.com/xap/1.0/",
+    "exif": "http://ns.adobe.com/exif/1.0/"
+  }
+
+  for ns, url in namespaces.items():
+      rdfDesc.setAttribute("xmlns:" + ns, url)
+
+  rdf.appendChild(rdfDesc)
+
+  if tags:
+    exifConf = root.createElement("exif:ComponentsConfiguration")
+    exifSeq = root.createElement("rdf:Seq")
+    for i in range(1, len(tags)-1):
+      exifli = root.createElement("rdf:li")
+      exifli.appendChild(root.createTextNode(str(i)))
+      exifSeq.appendChild(exifli)
+
+    exifli = root.createElement("rdf:li")
+    exifli.appendChild(root.createTextNode(str(0)))
+    exifSeq.appendChild(exifli)
+
+    exifConf.appendChild(exifSeq)
+    rdfDesc.appendChild(exifConf)
+
+    tagl = root.createElement("digiKam:TagsList")
+    tagSeq = root.createElement("rdf:Seq")
+    for tag in tags:
+      tagi = root.createElement("rdf:li")
+      tagi.appendChild(root.createTextNode(tag))
+      tagSeq.appendChild(tagi)
+
+    tagl.appendChild(tagSeq)
+    rdfDesc.appendChild(tagl)
+
+  xml.appendChild(rdf)
+
+  xml_str = '<?xpacket begin="" id="W5M0MpCehiHzreSzNTczkc9d"?>\n'
+  xml_str += root.toprettyxml(indent = " ").split("\n", 1)[1]
+  xml_str += '<?xpacket end="w"?>'
+
+  count+=1
+
+  with open(file, "w") as f:
+    f.write(xml_str)
+
+print("Generated %s XMP files" % count)