Bump to v0.1.1 (#1)

* Rename .html to .lxml
* use `lxml.html.fromstring` and `lxml.html.tostring` to process HTML
* use `lxml.etree.fromstring` and `lxml.etree.tostring` to process XML
* Add check_isort, check_black, check, check_all, fc: format_code into Makefile
* Update .travis.yml for linting check by isort and black
* Bump to v0.1.1

.gitignore

@@ -134,6 +134,8 @@ dmypy.json
 .vscode
 ## Makefile
 .black
+.check_black
+.check_isort
 .develop
 .flake
 .isort

.travis.yml

@@ -48,6 +48,14 @@ _helpers:
 
 jobs:
   include:
+    - <<: *_lint_base
+      name: Linting source code with isort
+      script:
+      - make check_isort
+    - <<: *_lint_base
+      name: Linting source code with black
+      script:
+      - make check_black
     - <<: *_lint_base
       name: Linting source code with flake8
       script:

CHANGES.md

@@ -1,7 +1,9 @@
 # Changelog
 
-## v0.1.0
+## v0.1.1
 
-- initialize project
-- add Extractor to extract data from the text which format is HTML or JSON.
-- add complex extractor: Field, Item
+- Rename `.html` to `.lxml`; Remove `fromstring`, `tostring` function from `.lxml`
+    * Rename .html to .lxml
+    * use `lxml.html.fromstring` and `lxml.html.tostring` to process HTML
+    * use `lxml.etree.fromstring` and `lxml.etree.tostring` to process XML
+- Add **check_isort**, **check_black**, **check**, **check_all**, **fc**: **format_code** into Makefile for development.

HISTORY.md

@@ -0,0 +1,5 @@
+## v0.1.0
+
+- initialize project
+- add Extractor to extract data from the text which format is HTML or JSON.
+- add complex extractor: Field, Item

Makefile

@@ -39,6 +39,13 @@ isort: .isort
 	isort -rc data_extractor tests
 	@touch .isort
 
+check_isort: .check_isort
+
+.check_isort: $(shell find data_extractor -type d) \
+		      $(shell find tests -type d)
+	isort -rc -c data_extractor tests
+	@touch .check_isort
+
 flake: .flake
 
 .flake: $(shell find data_extractor -type d) \
@@ -53,30 +60,54 @@ black: .black
 	black data_extractor tests
 	@touch .black
 
+check_black: .check_black
+
+.check_black: $(shell find data_extractor -type d) \
+		      $(shell find tests -type d)
+	black --check data_extractor tests
+	@touch .check_black
+
 mypy: .mypy
 
 .mypy: $(shell find data_extractor -type d)
 	mypy data_extractor
 	@touch .mypy
 
-.develop: $(shell find data_extractor -type d) .isort .black .flake
-	@touch .develop
+check: .check
+
+.check: $(shell find data_extractor -type d) \
+		$(shell find tests -type d) \
+		.check_isort .check_black .flake
+
+check_all: .check_all
+
+.check_all: $(shell find data_extractor -type d) \
+		$(shell find tests -type d) \
+		.check mypy
+
+format_code: .format_code
+fc: .format_code
+
+.format_code: $(shell find data_extractor -type d) \
+		      $(shell find tests -type d) \
+			  .isort .black
 
-test: .develop
+test: .check
 	pytest -q -x --ff --nf
 
-vtest: .develop
+vtest: .check
 	pytest -vv -x --ff --nf
 
-cov: .develop
+cov: .check
 	pytest -vv --cov=data_extractor
 	coverage html
 	@echo "open file://`pwd`/htmlcov/index.html to see coverage"
 
 clean:
 	@rm -f .black
 	@rm -f .coverage
-	@rm -f .develop
+	@rm -f .check_isort
+	@rm -f .check_black
 	@rm -f .flake
 	@rm -f .isort
 	@rm -f .mypy
@@ -91,7 +122,7 @@ build:
 	python setup.py sdist bdist_wheel
 
 
-.PHONY: all isort flake black mypy test vtest cov clean build
+.PHONY: all check check_isort check_black fc flake black isort mypy test vtest cov clean build
 
 endif
 endif

data_extractor/__init__.py

@@ -1 +1 @@
-__version__ = "0.1.0"
+__version__ = "0.1.1"

data_extractor/html.py → data_extractor/lxml.py

@@ -2,20 +2,19 @@
 from typing import List, Union
 
 # Third Party Library
-from lxml.etree import _Element as HTMLElement
-from lxml.html import fromstring, tostring
+from lxml.etree import _Element as Element
 
 # Local Folder
 from .abc import AbstractExtractor
 
 
 class CSSExtractor(AbstractExtractor):
-    def extract(self, element: HTMLElement) -> List[HTMLElement]:
+    def extract(self, element: Element) -> List[Element]:
         return element.cssselect(self.expr)
 
 
 class TextCSSExtractor(AbstractExtractor):
-    def extract(self, element: HTMLElement) -> List[str]:
+    def extract(self, element: Element) -> List[str]:
         return [ele.text for ele in CSSExtractor(self.expr).extract(element)]
 
 
@@ -27,7 +26,7 @@ def __init__(self, expr: str, attr: str):
     def __repr__(self) -> str:
         return f"{self.__class__.__name__}(expr={self.expr!r}, attr={self.attr!r})"
 
-    def extract(self, root: HTMLElement) -> List[str]:
+    def extract(self, root: Element) -> List[str]:
         return [
             ele.get(self.attr)
             for ele in CSSExtractor(self.expr).extract(root)
@@ -36,16 +35,14 @@ def extract(self, root: HTMLElement) -> List[str]:
 
 
 class XPathExtractor(AbstractExtractor):
-    def extract(self, element: HTMLElement) -> Union[List["HTMLElement"], List[str]]:
+    def extract(self, element: Element) -> Union[List["Element"], List[str]]:
         return element.xpath(self.expr)
 
 
 __all__ = (
     "AttrCSSExtractor",
     "CSSExtractor",
-    "HTMLElement",
+    "Element",
     "TextCSSExtractor",
     "XPathExtractor",
-    "fromstring",
-    "tostring",
 )

tests/test_item.py

@@ -1,9 +1,11 @@
 # Third Party Library
 import pytest
 
+from lxml.html import fromstring
+
 # Dsipder Module
-from data_extractor.html import XPathExtractor, fromstring
 from data_extractor.item import Field, Item
+from data_extractor.lxml import XPathExtractor
 
 
 @pytest.fixture(scope="module")

tests/test_html.py → tests/test_lxml.py

@@ -1,13 +1,10 @@
 # Third Party Library
 import pytest
 
+from lxml.html import fromstring
+
 # Dsipder Module
-from data_extractor.html import (
-    AttrCSSExtractor,
-    TextCSSExtractor,
-    XPathExtractor,
-    fromstring,
-)
+from data_extractor.lxml import AttrCSSExtractor, TextCSSExtractor, XPathExtractor
 
 
 @pytest.fixture(scope="module")