content-extraction 0.3.0__tar.gz → 0.3.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {content_extraction-0.3.0 → content_extraction-0.3.1}/PKG-INFO +2 -1
- {content_extraction-0.3.0 → content_extraction-0.3.1}/pyproject.toml +7 -2
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/PKG-INFO +2 -1
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/requires.txt +1 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/README.md +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/setup.cfg +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/__init__.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/common_std_io.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/do_ocr.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/dspy_modules.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/extract_from_pptx.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/file_handlers.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/fix_ocr.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/logging_config.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/parse_html.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/process.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/process_document.sh +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/semantic_chunk_html.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/split_and_create_digest.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/SOURCES.txt +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/dependency_links.txt +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/top_level.txt +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/tests/test_section_parser.py +0 -0
- {content_extraction-0.3.0 → content_extraction-0.3.1}/tests/test_semantic_chunk_html.py +0 -0
@@ -1,12 +1,13 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: content_extraction
|
3
|
-
Version: 0.3.
|
3
|
+
Version: 0.3.1
|
4
4
|
Summary: Project dedicated to content extraction from unstructured files that contain some useful information.
|
5
5
|
Requires-Python: >=3.12
|
6
6
|
Description-Content-Type: text/markdown
|
7
7
|
Requires-Dist: beautifulsoup4>=4.13.4
|
8
8
|
Requires-Dist: lxml>=6.0.0
|
9
9
|
Requires-Dist: python-pptx>=1.0.2
|
10
|
+
Requires-Dist: requests>=2.32.4
|
10
11
|
|
11
12
|
# HTML Content Extraction Tool
|
12
13
|
|
@@ -10,11 +10,16 @@ where = ["src"]
|
|
10
10
|
|
11
11
|
[project]
|
12
12
|
name = "content_extraction"
|
13
|
-
version = "0.3.
|
13
|
+
version = "0.3.1"
|
14
14
|
description = "Project dedicated to content extraction from unstructured files that contain some useful information."
|
15
15
|
readme = "README.md"
|
16
16
|
requires-python = ">=3.12"
|
17
|
-
dependencies = [
|
17
|
+
dependencies = [
|
18
|
+
"beautifulsoup4>=4.13.4",
|
19
|
+
"lxml>=6.0.0",
|
20
|
+
"python-pptx>=1.0.2",
|
21
|
+
"requests>=2.32.4",
|
22
|
+
]
|
18
23
|
|
19
24
|
[dependency-groups]
|
20
25
|
dev = [
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/PKG-INFO
RENAMED
@@ -1,12 +1,13 @@
|
|
1
1
|
Metadata-Version: 2.4
|
2
2
|
Name: content_extraction
|
3
|
-
Version: 0.3.
|
3
|
+
Version: 0.3.1
|
4
4
|
Summary: Project dedicated to content extraction from unstructured files that contain some useful information.
|
5
5
|
Requires-Python: >=3.12
|
6
6
|
Description-Content-Type: text/markdown
|
7
7
|
Requires-Dist: beautifulsoup4>=4.13.4
|
8
8
|
Requires-Dist: lxml>=6.0.0
|
9
9
|
Requires-Dist: python-pptx>=1.0.2
|
10
|
+
Requires-Dist: requests>=2.32.4
|
10
11
|
|
11
12
|
# HTML Content Extraction Tool
|
12
13
|
|
File without changes
|
File without changes
|
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/common_std_io.py
RENAMED
File without changes
|
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/dspy_modules.py
RENAMED
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/extract_from_pptx.py
RENAMED
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/file_handlers.py
RENAMED
File without changes
|
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/logging_config.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/process_document.sh
RENAMED
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction/semantic_chunk_html.py
RENAMED
File without changes
|
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/SOURCES.txt
RENAMED
File without changes
|
File without changes
|
{content_extraction-0.3.0 → content_extraction-0.3.1}/src/content_extraction.egg-info/top_level.txt
RENAMED
File without changes
|
File without changes
|
File without changes
|