fasthtmlparser 0.1.1__tar.gz → 0.1.3__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.
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/Cargo.lock +3 -3
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/Cargo.toml +2 -2
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/LICENSE.md +1 -1
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/PKG-INFO +4 -2
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/README.md +3 -1
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/pyproject.toml +1 -1
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/.gitattributes +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/.github/workflows/ci.yml +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/.gitignore +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/bench-results.md +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/python/fasthtmlparser/__init__.py +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/python/fasthtmlparser/_fasthtmlparser.pyi +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/python/fasthtmlparser/py.typed +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/src/lib.rs +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/tests/test_api.py +0 -0
- {fasthtmlparser-0.1.1 → fasthtmlparser-0.1.3}/tests/test_conformance.py +0 -0
|
@@ -4,16 +4,16 @@ version = 4
|
|
|
4
4
|
|
|
5
5
|
[[package]]
|
|
6
6
|
name = "fasthtmlparser"
|
|
7
|
-
version = "0.1.
|
|
7
|
+
version = "0.1.3"
|
|
8
8
|
source = "registry+https://github.com/rust-lang/crates.io-index"
|
|
9
|
-
checksum = "
|
|
9
|
+
checksum = "ea710fb913347a13edeb7f1c7e3cb3e01c2ad7522a1524f5d983796bc63ebc18"
|
|
10
10
|
dependencies = [
|
|
11
11
|
"memchr",
|
|
12
12
|
]
|
|
13
13
|
|
|
14
14
|
[[package]]
|
|
15
15
|
name = "fasthtmlparser-py"
|
|
16
|
-
version = "0.1.
|
|
16
|
+
version = "0.1.3"
|
|
17
17
|
dependencies = [
|
|
18
18
|
"fasthtmlparser",
|
|
19
19
|
"pyo3",
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[package]
|
|
2
2
|
name = "fasthtmlparser-py"
|
|
3
|
-
version = "0.1.
|
|
3
|
+
version = "0.1.3"
|
|
4
4
|
edition = "2021"
|
|
5
5
|
publish = false
|
|
6
6
|
readme = "README.md"
|
|
@@ -10,7 +10,7 @@ name = "_fasthtmlparser"
|
|
|
10
10
|
crate-type = ["cdylib"]
|
|
11
11
|
|
|
12
12
|
[dependencies]
|
|
13
|
-
fasthtmlparser = "0.1"
|
|
13
|
+
fasthtmlparser = "0.1.3"
|
|
14
14
|
pyo3 = { version = "0.30", features = ["extension-module", "abi3-py310", "generate-import-lib"] }
|
|
15
15
|
|
|
16
16
|
[profile.release]
|
|
@@ -53,7 +53,7 @@ more**, the Licensee must purchase a Commercial License.
|
|
|
53
53
|
- A Licensee that stops being a Small Licensee (its Annual Revenue or Headcount reaches the
|
|
54
54
|
threshold) while already using the Software must purchase the Commercial License within
|
|
55
55
|
30 days.
|
|
56
|
-
- To purchase: https://
|
|
56
|
+
- To purchase: https://fasthtmlparser.com/#pricing, or contact **romanti3172@gmail.com** for an invoice.
|
|
57
57
|
|
|
58
58
|
The Commercial License grants the same rights as section 2, without the revenue and headcount
|
|
59
59
|
limits.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: fasthtmlparser
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.3
|
|
4
4
|
Classifier: Development Status :: 4 - Beta
|
|
5
5
|
Classifier: Intended Audience :: Developers
|
|
6
6
|
Classifier: Programming Language :: Python :: 3
|
|
@@ -27,6 +27,8 @@ Project-URL: Source, https://github.com/romanti3172/fasthtmlparser-py
|
|
|
27
27
|
[](https://github.com/romanti3172/fasthtmlparser-py/actions/workflows/ci.yml)
|
|
28
28
|
[](https://pypi.org/project/fasthtmlparser/)
|
|
29
29
|
|
|
30
|
+
**Website:** [fasthtmlparser.com](https://fasthtmlparser.com): try the parser on any page, documentation and every language.
|
|
31
|
+
|
|
30
32
|
A fast HTML / XML parser for scraping, with **XPath 1.0** and **CSS selectors**: Python bindings of the
|
|
31
33
|
[Rust port](https://github.com/romanti3172/fasthtmlparser-rs) of
|
|
32
34
|
[z3l.FastHtmlParser](https://github.com/romanti3172/z3l.FastHtmlParser). It is built for extracting data, not for
|
|
@@ -107,7 +109,7 @@ tree construction (no implied `<tbody>` or `<html>`), and documents are read-onl
|
|
|
107
109
|
|
|
108
110
|
## Same results as the .NET version
|
|
109
111
|
|
|
110
|
-
`tests/test_conformance.py` runs the conformance data of the Rust crate through the Python package: on
|
|
112
|
+
`tests/test_conformance.py` runs the conformance data of the Rust crate through the Python package: on 121 pages
|
|
111
113
|
(fixtures, broken markup, cut-off pages, CR LF, 600-deep nesting, ...) every tag's name, position, text, text with line
|
|
112
114
|
breaks, attributes, navigation and links, and 569 XPath / CSS queries on the document and from three tags of each
|
|
113
115
|
page, must give exactly what z3l.FastHtmlParser (.NET) gives. So the bindings are checked as well as the parser.
|
|
@@ -3,6 +3,8 @@
|
|
|
3
3
|
[](https://github.com/romanti3172/fasthtmlparser-py/actions/workflows/ci.yml)
|
|
4
4
|
[](https://pypi.org/project/fasthtmlparser/)
|
|
5
5
|
|
|
6
|
+
**Website:** [fasthtmlparser.com](https://fasthtmlparser.com): try the parser on any page, documentation and every language.
|
|
7
|
+
|
|
6
8
|
A fast HTML / XML parser for scraping, with **XPath 1.0** and **CSS selectors**: Python bindings of the
|
|
7
9
|
[Rust port](https://github.com/romanti3172/fasthtmlparser-rs) of
|
|
8
10
|
[z3l.FastHtmlParser](https://github.com/romanti3172/z3l.FastHtmlParser). It is built for extracting data, not for
|
|
@@ -83,7 +85,7 @@ tree construction (no implied `<tbody>` or `<html>`), and documents are read-onl
|
|
|
83
85
|
|
|
84
86
|
## Same results as the .NET version
|
|
85
87
|
|
|
86
|
-
`tests/test_conformance.py` runs the conformance data of the Rust crate through the Python package: on
|
|
88
|
+
`tests/test_conformance.py` runs the conformance data of the Rust crate through the Python package: on 121 pages
|
|
87
89
|
(fixtures, broken markup, cut-off pages, CR LF, 600-deep nesting, ...) every tag's name, position, text, text with line
|
|
88
90
|
breaks, attributes, navigation and links, and 569 XPath / CSS queries on the document and from three tags of each
|
|
89
91
|
page, must give exactly what z3l.FastHtmlParser (.NET) gives. So the bindings are checked as well as the parser.
|
|
@@ -4,7 +4,7 @@ build-backend = "maturin"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "fasthtmlparser"
|
|
7
|
-
version = "0.1.
|
|
7
|
+
version = "0.1.3"
|
|
8
8
|
description = "Fast HTML / XML parser for scraping with XPath 1.0 and CSS selectors, in Rust. A port of z3l.FastHtmlParser."
|
|
9
9
|
readme = "README.md"
|
|
10
10
|
license = "LicenseRef-z3l-FastHtmlParser"
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|