From f5debc6f56c6bd153db789e7cf8145e5f2acaf7a Mon Sep 17 00:00:00 2001
From: hyugogirubato <65763543+hyugogirubato@users.noreply.github.com>
Date: Wed, 8 Feb 2023 19:51:08 +0100
Subject: [PATCH] Support remote files + binary files

---
 .idea/.gitignore                              |  0
 .idea/inspectionProfiles/Project_Default.xml  | 12 ++++
 .../inspectionProfiles/profiles_settings.xml  |  6 ++
 .idea/misc.xml                                |  4 ++
 .idea/modules.xml                             |  8 +++
 .idea/pycbzhelper.iml                         | 12 ++++
 .idea/vcs.xml                                 |  6 ++
 .idea/workspace.xml                           | 55 +++++++++++++++++++
 pycbzhelper/exceptions.py                     |  4 ++
 pycbzhelper/helper.py                         | 13 ++++-
 10 files changed, 119 insertions(+), 1 deletion(-)
 create mode 100644 .idea/.gitignore
 create mode 100644 .idea/inspectionProfiles/Project_Default.xml
 create mode 100644 .idea/inspectionProfiles/profiles_settings.xml
 create mode 100644 .idea/misc.xml
 create mode 100644 .idea/modules.xml
 create mode 100644 .idea/pycbzhelper.iml
 create mode 100644 .idea/vcs.xml
 create mode 100644 .idea/workspace.xml

diff --git a/.idea/.gitignore b/.idea/.gitignore
new file mode 100644
index 0000000..e69de29
diff --git a/.idea/inspectionProfiles/Project_Default.xml b/.idea/inspectionProfiles/Project_Default.xml
new file mode 100644
index 0000000..d2c483e
--- /dev/null
+++ b/.idea/inspectionProfiles/Project_Default.xml
@@ -0,0 +1,12 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="str.unescape" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>
\ No newline at end of file
diff --git a/.idea/inspectionProfiles/profiles_settings.xml b/.idea/inspectionProfiles/profiles_settings.xml
new file mode 100644
index 0000000..105ce2d
--- /dev/null
+++ b/.idea/inspectionProfiles/profiles_settings.xml
@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file
diff --git a/.idea/misc.xml b/.idea/misc.xml
new file mode 100644
index 0000000..a2e120d
--- /dev/null
+++ b/.idea/misc.xml
@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file
diff --git a/.idea/modules.xml b/.idea/modules.xml
new file mode 100644
index 0000000..94fb310
--- /dev/null
+++ b/.idea/modules.xml
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/pycbzhelper.iml" filepath="$PROJECT_DIR$/.idea/pycbzhelper.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file
diff --git a/.idea/pycbzhelper.iml b/.idea/pycbzhelper.iml
new file mode 100644
index 0000000..3f370ba
--- /dev/null
+++ b/.idea/pycbzhelper.iml
@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="Python 3.7" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+</module>
\ No newline at end of file
diff --git a/.idea/vcs.xml b/.idea/vcs.xml
new file mode 100644
index 0000000..94a25f7
--- /dev/null
+++ b/.idea/vcs.xml
@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>
\ No newline at end of file
diff --git a/.idea/workspace.xml b/.idea/workspace.xml
new file mode 100644
index 0000000..9187d4f
--- /dev/null
+++ b/.idea/workspace.xml
@@ -0,0 +1,55 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ChangeListManager">
+    <list default="true" id="1e3b2b5c-bbd5-4f54-89d8-f73775e9feba" name="Default Changelist" comment="">
+      <change beforePath="$PROJECT_DIR$/.gitignore" beforeDir="false" afterPath="$PROJECT_DIR$/.gitignore" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/.travis.yml" beforeDir="false" afterPath="$PROJECT_DIR$/.travis.yml" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/LICENSE" beforeDir="false" afterPath="$PROJECT_DIR$/LICENSE" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/README.md" beforeDir="false" afterPath="$PROJECT_DIR$/README.md" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/pycbzhelper/__init__.py" beforeDir="false" afterPath="$PROJECT_DIR$/pycbzhelper/__init__.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/pycbzhelper/comicinfo.py" beforeDir="false" afterPath="$PROJECT_DIR$/pycbzhelper/comicinfo.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/pycbzhelper/exceptions.py" beforeDir="false" afterPath="$PROJECT_DIR$/pycbzhelper/exceptions.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/pycbzhelper/helper.py" beforeDir="false" afterPath="$PROJECT_DIR$/pycbzhelper/helper.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/pycbzhelper/utils.py" beforeDir="false" afterPath="$PROJECT_DIR$/pycbzhelper/utils.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/setup.py" beforeDir="false" afterPath="$PROJECT_DIR$/setup.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/tests.py" beforeDir="false" afterPath="$PROJECT_DIR$/tests.py" afterDir="false" />
+    </list>
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="Git.Settings">
+    <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
+  </component>
+  <component name="ProjectId" id="2LRm1wsZXqsVSpU3IHCZQJU0e6s" />
+  <component name="ProjectLevelVcsManager" settingsEditedManually="true" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent">
+    <property name="RunOnceActivity.OpenProjectViewOnStart" value="true" />
+    <property name="RunOnceActivity.ShowReadmeOnStart" value="true" />
+    <property name="WebServerToolWindowFactoryState" value="false" />
+    <property name="last_opened_file_path" value="$PROJECT_DIR$" />
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="1e3b2b5c-bbd5-4f54-89d8-f73775e9feba" name="Default Changelist" comment="" />
+      <created>1675842063151</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1675842063151</updated>
+      <workItem from="1675842067503" duration="60000" />
+      <workItem from="1675871067263" duration="307000" />
+      <workItem from="1675879384779" duration="29000" />
+      <workItem from="1675881442099" duration="621000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+</project>
\ No newline at end of file
diff --git a/pycbzhelper/exceptions.py b/pycbzhelper/exceptions.py
index 8e47152..86db50e 100644
--- a/pycbzhelper/exceptions.py
+++ b/pycbzhelper/exceptions.py
@@ -12,3 +12,7 @@ class MissingPageFile(PyCBZHelperException):
 
 class InvalidFilePermission(PyCBZHelperException):
     """Unable to delete existing file."""
+
+
+class FileNotFound(PyCBZHelperException):
+    """The specified source file was not found."""
diff --git a/pycbzhelper/helper.py b/pycbzhelper/helper.py
index d958843..2836834 100644
--- a/pycbzhelper/helper.py
+++ b/pycbzhelper/helper.py
@@ -3,12 +3,13 @@ import pathlib
 import shutil
 import zipfile
 
+import requests
 from json2xml import json2xml
 from langcodes import Language
 from PIL import Image
 
 from pycbzhelper.comicinfo import KEYS_STRING, KEYS_INT, KEYS_SPECIAL, KEYS_AGE, KEYS_FORMAT, KEYS_PAGE_TYPE
-from pycbzhelper.exceptions import InvalidKeyValue, MissingPageFile, InvalidFilePermission
+from pycbzhelper.exceptions import InvalidKeyValue, MissingPageFile, InvalidFilePermission, FileNotFound
 from pycbzhelper.utils import get_key_value, delete_none, slugify
 
 
@@ -60,6 +61,16 @@ class Helper:
             kwargs['PageCount'] = len(kwargs.get('Pages'))
             for i in range(kwargs.get('PageCount')):
                 page = kwargs.get('Pages')[i]
+                if isinstance(page['File'], bytes) or (isinstance(page['File'], str) and page['File'].startswith('https://')):
+                    file = os.path.join("tmp", f"page-{i:03d}.jpg")
+                    with open(file, mode="wb") as f:
+                        f.write(page['File'] if isinstance(page['File'], bytes) else requests.get(url=page['File']).content)
+                        f.close()
+                    page['File'] = file
+
+                if not os.path.exists(page['File']):
+                    raise FileNotFound(f"ERROR: Source file is invalid: {page['File']}")
+
                 properties = Image.open(page['File'])
                 self._files.append(page['File'])
                 if not page.get('Type'):