Merge pull request #35 from iscc/titusz/mobi-support

Add mobi support

README.md

@@ -27,7 +27,7 @@ This tool offers an easy way to generate ISCC codes from the command line. It su
 
 #### Text
 
-doc, docx, epub, html, odt, pdf, rtf, txt, xml, ibooks, md, xls ...
+doc, docx, epub, html, odt, pdf, rtf, txt, xml, ibooks, md, xls, mobi ...
 
 
 #### Image
@@ -199,6 +199,9 @@ You may also want join our developer chat on Telegram at <https://t.me/iscc_dev>
 
 ## Change Log
 
+### [0.9.4] - 2020-03-02
+- Add experimental support for mobi files
+
 ### [0.9.3] - 2020-02-18
 - Add support for XHTML
 - Fix error on unsupported media types

iscc_cli/__init__.py

@@ -3,10 +3,11 @@
 import click
 from tika import tika
 
-__version__ = "0.9.3"
+__version__ = "0.9.4"
 
 APP_NAME = "iscc-cli"
 APP_DIR = click.get_app_dir(APP_NAME, roaming=False)
 os.makedirs(iscc_cli.APP_DIR, exist_ok=True)
 os.environ["TIKA_PATH"] = APP_DIR
+os.environ["LOGURU_AUTOINIT"] = "False"
 tika.log.disabled = True

iscc_cli/batch.py

@@ -1,6 +1,8 @@
 # -*- coding: utf-8 -*-
+import shutil
 from os.path import basename, abspath
 import click
+import mobi
 from tika import detector, parser
 import iscc
 
@@ -41,7 +43,17 @@ def batch(path, recursive, guess):
             )
             continue
 
-        tika_result = parser.from_file(f)
+        if media_type == "application/x-mobipocket-ebook":
+            try:
+                tempdir, epub_filepath = mobi.extract(f)
+                tika_result = parser.from_file(epub_filepath)
+                shutil.rmtree(tempdir)
+            except Exception as e:
+                click.echo("Error with mobi extraction %s" % f)
+                continue
+        else:
+            tika_result = parser.from_file(f)
+
         title = get_title(tika_result, guess=guess)
 
         mid, norm_title, _ = iscc.meta_id(title)

iscc_cli/const.py

@@ -32,7 +32,11 @@ class GMT:
         "gmt": GMT.TEXT,
         "ext": "xlsx",
     },
-    "application/vnd.ms-excel": {"gmt": GMT.TEXT, "ext": "xls",},
+    "application/vnd.ms-excel": {"gmt": GMT.TEXT, "ext": "xls"},
+    "application/x-mobipocket-ebook": {
+        "gmt": GMT.TEXT,
+        "ext": ["mobi", "prc", "azw", "azw3", "azw4"],
+    },
     # Image Formats
     "image/bmp": {"gmt": GMT.IMAGE, "ext": "bmp"},
     "image/gif": {"gmt": GMT.IMAGE, "ext": "gif"},

iscc_cli/dump.py

@@ -1,8 +1,12 @@
 # -*- coding: utf-8 -*-
+import shutil
+
 import click
+import mobi
 from click import UsageError
-from tika import parser
+from tika import parser, detector
 from iscc_cli.utils import DefaultHelp
+from iscc_cli.const import SUPPORTED_MIME_TYPES
 import json
 
 
@@ -15,7 +19,19 @@
 @click.option("-c", "--content", is_flag=True, default=False, help="Dump content only.")
 def dump(file, strip, meta, content):
     """Dump Tika extraction results for FILE."""
-    tika_result = parser.from_file(file.name)
+
+    media_type = detector.from_file(file.name)
+    if media_type not in SUPPORTED_MIME_TYPES:
+        click.echo("Unsupported media type {}.".format(media_type))
+        click.echo("Please request support at https://github.com/iscc/iscc-cli/issues")
+
+    if media_type == "application/x-mobipocket-ebook":
+        tempdir, epub_filepath = mobi.extract(file.name)
+        tika_result = parser.from_file(epub_filepath)
+        shutil.rmtree(tempdir)
+    else:
+        tika_result = parser.from_file(file.name)
+
     if all([meta, content]):
         raise UsageError("Use either --meta or --content for selective output.")
 

iscc_cli/gen.py

@@ -1,8 +1,10 @@
 # -*- coding: utf-8 -*-
+import shutil
 from os.path import abspath
 
 import click
 import iscc
+import mobi
 from tika import detector, parser
 
 from iscc_cli import audio_id, video_id, fpcalc
@@ -31,7 +33,13 @@ def gen(file, guess, title, extra, verbose):
         click.echo("Unsupported media type {}.".format(media_type))
         click.echo("Please request support at https://github.com/iscc/iscc-cli/issues")
 
-    tika_result = parser.from_file(file.name)
+    if media_type == "application/x-mobipocket-ebook":
+        tempdir, epub_filepath = mobi.extract(file.name)
+        tika_result = parser.from_file(epub_filepath)
+        shutil.rmtree(tempdir)
+    else:
+        tika_result = parser.from_file(file.name)
+
     if not title:
         title = get_title(tika_result, guess=guess)