chore: init commit

.github/FUNDING.yml

@@ -0,0 +1,13 @@
+# These are supported funding model platforms
+
+github: # Replace with up to 4 GitHub Sponsors-enabled usernames e.g., [user1, user2]
+patreon: # Replace with a single Patreon username
+open_collective: # Replace with a single Open Collective username
+ko_fi: # Replace with a single Ko-fi username
+tidelift: # Replace with a single Tidelift platform-name/package-name e.g., npm/babel
+community_bridge: # Replace with a single Community Bridge project-name e.g., cloud-foundry
+liberapay: # Replace with a single Liberapay username
+issuehunt: # Replace with a single IssueHunt username
+otechie: # Replace with a single Otechie username
+lfx_crowdfunding: # Replace with a single LFX Crowdfunding project-name e.g., cloud-foundry
+custom: https://raw.githubusercontent.com/RapidAI/.github/6db6b6b9273f3151094a462a61fbc8e88564562c/assets/Sponsor.png

.github/workflows/SyncToGitee.yml

@@ -0,0 +1,22 @@
+name: SyncToGitee
+on:
+  push:
+    branches:
+      - main
+jobs:
+  repo-sync:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout source codes
+        uses: actions/checkout@v3
+
+      - name: Mirror the Github organization repos to Gitee.
+        uses: Yikun/[email protected]
+        with:
+          src: 'github/SWHL'
+          dst: 'gitee/SWHL'
+          dst_key: ${{ secrets.GITEE_PRIVATE_KEY }}
+          dst_token:  ${{ secrets.GITEE_TOKEN }}
+          force_update: true
+          static_list: "BaiduImageSpider"
+          debug: true

.github/workflows/publish_whl.yml

@@ -0,0 +1,53 @@
+name: Push baidu_image_spider to pypi
+
+on:
+  push:
+    tags:
+      - v*
+
+jobs:
+  UnitTesting:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Pull latest code
+        uses: actions/checkout@v3
+
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+          architecture: 'x64'
+
+      - name: Display Python version
+        run: python -c "import sys; print(sys.version)"
+
+      - name: Unit testings
+        run: |
+          pytest tests/test_main.py
+
+  GenerateWHL_PushPyPi:
+    needs: UnitTesting
+    runs-on: ubuntu-latest
+
+    steps:
+      - uses: actions/checkout@v3
+
+      - name: Set up Python 3.10
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.10'
+          architecture: 'x64'
+
+      - name: Run setup
+        run: |
+          pip install -r requirements.txt
+          python -m pip install --upgrade pip
+          pip install wheel get_pypi_latest_version
+
+          python setup.py bdist_wheel ${{ github.ref_name }}
+
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/[email protected]
+        with:
+          password: ${{ secrets.BAIDUIMAGESPIDER }}
+          packages_dir: dist/

.gitignore

@@ -0,0 +1,164 @@
+outputs/
+*.json
+
+# Created by .ignore support plugin (hsz.mobi)
+### Python template
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+.pytest_cache
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+# *.manifest
+# *.spec
+*.res
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+#idea
+.vs
+.vscode
+.idea
+/images
+/models
+
+#models
+*.onnx
+
+*.ttf
+*.ttc
+
+long1.jpg
+
+*.bin
+*.mapping
+*.xml
+
+*.pdiparams
+*.pdiparams.info
+*.pdmodel
+
+.DS_Store
+*.pth
+/rapid_table_torch/models/*.pth
+/rapid_table_torch/models/*.json

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+repos:
+- repo: https://gitee.com/SWHL/autoflake
+  rev: v2.1.1
+  hooks:
+    - id: autoflake
+      args:
+        [
+          "--recursive",
+          "--in-place",
+          "--remove-all-unused-imports",
+          "--remove-unused-variable",
+          "--ignore-init-module-imports",
+        ]
+      files: \.py$
+- repo: https://gitee.com/SWHL/black
+  rev: 23.1.0
+  hooks:
+    - id: black
+      files: \.py$

README.md

@@ -0,0 +1,47 @@
+## Baidu Image Spider
+
+一个超级轻量的百度图片爬虫, modified from <https://github.com/kong36088/BaiduImageSpider>
+
+### 安装
+
+```bash
+pip install baidu_image_spider
+```
+
+### Python使用
+
+```python
+from baidu_image_spider.main import Crawler
+
+crawler = Crawler(0.05, save_dir="outputs")  # 抓取延迟为 0.05
+
+# 抓取关键词为 “美女”，总数为2页，开始页码为1，每页 30 张, 即总共2*30=60张
+crawler(word="美女", total_page=2, start_page=1, per_page=30)
+```
+
+### 终端使用
+
+```bash
+baidu_image_spider -w 美女 -tp 1 -sp 1 -pp 2
+```
+
+查看参数文档：
+
+```bash
+$ baidu_image_spider -h
+usage: baidu_image_spider [-h] -w WORD -tp TOTAL_PAGE -sp START_PAGE [-pp [PER_PAGE]] [-sd SAVE_DIR] [-d DELAY]
+
+options:
+  -h, --help            show this help message and exit
+  -w WORD, --word WORD  抓取关键词
+  -tp TOTAL_PAGE, --total_page TOTAL_PAGE
+                        需要抓取的总页数
+  -sp START_PAGE, --start_page START_PAGE
+                        起始页数
+  -pp [PER_PAGE], --per_page [PER_PAGE]
+                        每页大小
+  -sd SAVE_DIR, --save_dir SAVE_DIR
+                        图片保存目录
+  -d DELAY, --delay DELAY
+                        抓取延时（间隔）
+```

baidu_image_spider/__init__.py

@@ -0,0 +1,3 @@
+# -*- encoding: utf-8 -*-
+# @Author: SWHL
+# @Contact: [email protected]