freecrawl 0.0.1__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.
Files changed (9) hide show
  1. freecrawl-0.0.1/PKG-INFO +25 -0
  2. freecrawl-0.0.1/README.md +10 -0
  3. freecrawl-0.0.1/pyproject.toml +25 -0
  4. freecrawl-0.0.1/setup.cfg +4 -0
  5. freecrawl-0.0.1/src/freecrawl/__init__.py +3 -0
  6. freecrawl-0.0.1/src/freecrawl.egg-info/PKG-INFO +25 -0
  7. freecrawl-0.0.1/src/freecrawl.egg-info/SOURCES.txt +7 -0
  8. freecrawl-0.0.1/src/freecrawl.egg-info/dependency_links.txt +1 -0
  9. freecrawl-0.0.1/src/freecrawl.egg-info/top_level.txt +1 -0
freecrawl-0.0.1/PKG-INFO ADDED
@@ -0,0 +1,25 @@
1
+ Metadata-Version: 2.4
2
+ Name: freecrawl
3
+ Version: 0.0.1
4
+ Summary: A minimal, extensible web crawling framework. Write a spider once, reuse it forever.
5
+ Author: DiscourseLab
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://freecrawl.dev
8
+ Project-URL: Source, https://github.com/freecrawl
9
+ Keywords: crawler,scraper,spider,web-scraping
10
+ Classifier: Development Status :: 1 - Planning
11
+ Classifier: Programming Language :: Python :: 3
12
+ Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
13
+ Requires-Python: >=3.10
14
+ Description-Content-Type: text/markdown
15
+
16
+ # freecrawl
17
+
18
+ A minimal, extensible web crawling framework that runs on your machine.
19
+
20
+ Give it a URL, and it writes a reusable spider: URL rules plus extraction config,
21
+ saved to a database so the same site never has to be figured out twice. Discovery
22
+ sources, transports, extractors, and sinks are single-file extensions.
23
+
24
+ This is a placeholder release. The framework is under development at
25
+ https://github.com/freecrawl and https://freecrawl.dev.
freecrawl-0.0.1/README.md ADDED
@@ -0,0 +1,10 @@
1
+ # freecrawl
2
+
3
+ A minimal, extensible web crawling framework that runs on your machine.
4
+
5
+ Give it a URL, and it writes a reusable spider: URL rules plus extraction config,
6
+ saved to a database so the same site never has to be figured out twice. Discovery
7
+ sources, transports, extractors, and sinks are single-file extensions.
8
+
9
+ This is a placeholder release. The framework is under development at
10
+ https://github.com/freecrawl and https://freecrawl.dev.
freecrawl-0.0.1/pyproject.toml ADDED
@@ -0,0 +1,25 @@
1
+ [build-system]
2
+ requires = ["setuptools>=68"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "freecrawl"
7
+ version = "0.0.1"
8
+ description = "A minimal, extensible web crawling framework. Write a spider once, reuse it forever."
9
+ readme = "README.md"
10
+ license = "Apache-2.0"
11
+ requires-python = ">=3.10"
12
+ authors = [{ name = "DiscourseLab" }]
13
+ keywords = ["crawler", "scraper", "spider", "web-scraping"]
14
+ classifiers = [
15
+ "Development Status :: 1 - Planning",
16
+ "Programming Language :: Python :: 3",
17
+ "Topic :: Internet :: WWW/HTTP :: Indexing/Search",
18
+ ]
19
+
20
+ [project.urls]
21
+ Homepage = "https://freecrawl.dev"
22
+ Source = "https://github.com/freecrawl"
23
+
24
+ [tool.setuptools.packages.find]
25
+ where = ["src"]
freecrawl-0.0.1/setup.cfg ADDED
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
freecrawl-0.0.1/src/freecrawl/__init__.py ADDED
@@ -0,0 +1,3 @@
1
+ """freecrawl: a minimal, extensible web crawling framework."""
2
+
3
+ __version__ = "0.0.1"
freecrawl-0.0.1/src/freecrawl.egg-info/PKG-INFO ADDED
@@ -0,0 +1,25 @@
1
+ Metadata-Version: 2.4
2
+ Name: freecrawl
3
+ Version: 0.0.1
4
+ Summary: A minimal, extensible web crawling framework. Write a spider once, reuse it forever.
5
+ Author: DiscourseLab
6
+ License-Expression: Apache-2.0
7
+ Project-URL: Homepage, https://freecrawl.dev
8
+ Project-URL: Source, https://github.com/freecrawl
9
+ Keywords: crawler,scraper,spider,web-scraping
10
+ Classifier: Development Status :: 1 - Planning
11
+ Classifier: Programming Language :: Python :: 3
12
+ Classifier: Topic :: Internet :: WWW/HTTP :: Indexing/Search
13
+ Requires-Python: >=3.10
14
+ Description-Content-Type: text/markdown
15
+
16
+ # freecrawl
17
+
18
+ A minimal, extensible web crawling framework that runs on your machine.
19
+
20
+ Give it a URL, and it writes a reusable spider: URL rules plus extraction config,
21
+ saved to a database so the same site never has to be figured out twice. Discovery
22
+ sources, transports, extractors, and sinks are single-file extensions.
23
+
24
+ This is a placeholder release. The framework is under development at
25
+ https://github.com/freecrawl and https://freecrawl.dev.
freecrawl-0.0.1/src/freecrawl.egg-info/SOURCES.txt ADDED
@@ -0,0 +1,7 @@
1
+ README.md
2
+ pyproject.toml
3
+ src/freecrawl/__init__.py
4
+ src/freecrawl.egg-info/PKG-INFO
5
+ src/freecrawl.egg-info/SOURCES.txt
6
+ src/freecrawl.egg-info/dependency_links.txt
7
+ src/freecrawl.egg-info/top_level.txt
freecrawl-0.0.1/src/freecrawl.egg-info/top_level.txt ADDED
@@ -0,0 +1 @@
1
+ freecrawl