Initial Commit

.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

.gitignore

@@ -0,0 +1,152 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+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
+
+# 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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2022 Ivan Šincek
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MANIFEST.in

@@ -0,0 +1 @@
+include src/nagooglesearch/*.py

README.md

@@ -0,0 +1,178 @@
+# Not Another Google Search
+
+Not another Google searching library. Just kidding - it is.
+
+Made for educational purposes. I hope it will help!
+
+Future plans:
+
+* ability to set/rotate search parameters, user agents, and proxies without reinitialization.
+
+## Table of Contents
+
+* [How to Install](#how-to-install)
+	* [Standard Install](#standard-install)
+	* [Build and Install From the Source](#build-and-install-from-the-source)
+* [Usage](#usage)
+	* [Standard](#standard)
+	* [Shortest Possible](#shortest-possible)
+	* [Time Sensitive Search](#time-sensitive-search)
+	* [User Agents](#user-agents)
+
+## How to Install
+
+### Standard Install
+
+```bash
+pip3 install nagooglesearch
+
+pip3 install --upgrade nagooglesearch
+```
+
+### Build and Install From the Source
+
+Run the following commands:
+
+```bash
+git clone https://github.com/ivan-sincek/nagooglesearch && cd nagooglesearch
+
+python3 -m pip install --upgrade build
+
+python3 -m build
+
+python3 -m pip install dist/nagooglesearch-8.0-py3-none-any.whl
+```
+
+## Usage
+
+### Standard
+
+Default values:
+
+```python
+nagooglesearch.GoogleClient(
+	tld = "com",
+	homepage_parameters = {
+		"btnK": "Google+Search",
+		"source": "hp"
+	},
+	search_parameters = {
+	},
+	user_agent = "",
+	proxy = "",
+	max_results = 100,
+	min_sleep = 8,
+	max_sleep = 18,
+	debug = False
+)
+```
+
+**Only domains without they keyword `google` and not ending with the keyword `goo.gl` are accepted as valid results. The final output is a unique and sorted list of URLs.**
+
+Example, standard:
+
+```python
+import nagooglesearch
+
+# the following query string parameters are set only if 'start' query string parameter is not set or is equal to zero
+# simulate a homepage search
+homepage_parameters = {
+	"btnK": "Google+Search",
+	"source": "hp"
+}
+
+# search the internet for additional query string parameters
+search_parameters = {
+	"q": "site:*.example.com intext:password", # search query
+	"tbs": "li:1", # specify 'li:1' for verbatim search (no alternate spellings, etc.)
+	"hl": "en",
+	"lr": "lang_en",
+	"cr": "countryUS",
+	"filter": "0", # specify '0' to display hidden results
+	"safe": "images", # specify 'images' to turn off safe search, or specify 'active' to turn on safe search
+	"num": "80" # number of results per page
+}
+
+client = nagooglesearch.GoogleClient(
+	tld = "com", # top level domain, e.g., www.google.com or www.google.hr
+	homepage_parameters = homepage_parameters, # 'search_parameters' will override 'homepage_parameters'
+	search_parameters = search_parameters,
+	user_agent = "curl/3.30.1", # a random user agent will be set if none is provided
+	proxy = "socks5://127.0.0.1:9050", # one of the supported URL schemes are 'http[s]', 'socks4[h]', and 'socks5[h]'
+	max_results = 200, # maximum unique URLs to return
+	min_sleep = 15, # minimum sleep between page requests
+	max_sleep = 30, # maximum sleep between page requests
+	debug = True # enable debug output
+)
+
+urls = client.search()
+
+if client.get_error() == "REQUESTS_EXCEPTION":
+	print("[ Requests Exception ]")
+	# do something
+elif client.get_error() == "429_TOO_MANY_REQUESTS":
+	print("[ HTTP 429 Too Many Requests ]")
+	# do something
+
+for url in urls:
+	print(url)
+	# do something
+```
+
+If `max_results` is set to, e.g., `200` and `num` is set to, e.g., `80`, then, maximum unique URLs that could be returned could actually reach `240`.
+
+Check the list of user agents [here](https://github.com/ivan-sincek/bot-safe-agents/blob/main/src/bot_safe_agents/user_agents.txt). For more user agents, check [scrapeops.io](https://scrapeops.io).
+
+### Shortest Possible
+
+Example, shortest possible:
+
+```python
+import nagooglesearch
+
+urls = nagooglesearch.GoogleClient(search_parameters = {"q": "site:*.example.com intext:password"}).search()
+
+# do something
+```
+
+### Time Sensitive Search
+
+Example, do not show results older than 6 months:
+
+```python
+import nagooglesearch, dateutil.relativedelta as relativedelta
+
+def get_tbs(months):
+	today = datetime.datetime.today()
+	return nagooglesearch.get_tbs(today, today - relativedelta.relativedelta(months = months))
+
+search_parameters = {
+	"tbs": get_tbs(6)
+}
+
+# do something
+```
+
+### User Agents
+
+Example, get all user agents:
+
+```python
+import nagooglesearch
+
+user_agents = nagooglesearch.get_all_user_agents()
+print(user_agents)
+
+# do something
+```
+
+Example, get a random user agent:
+
+```python
+import nagooglesearch
+
+user_agent = nagooglesearch.get_random_user_agent()
+print(user_agent)
+
+# do something
+```

pyproject.toml

@@ -0,0 +1,23 @@
+[build-system]
+requires = ["setuptools>=75.3.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "nagooglesearch"
+version = "8.0"
+authors = [{ name = "Ivan Sincek" }]
+description = "Not another Google searching tool."
+readme = "README.md"
+requires-python = ">=3.10"
+classifiers = [
+	"Programming Language :: Python :: 3",
+	"License :: OSI Approved :: MIT License",
+	"Operating System :: OS Independent"
+]
+dependencies = ["bot_safe_agents>=1.0", "requests>=2.31.0", "bs4>=0.0.1", "beautifulsoup4>=4.12.3"]
+
+[project.urls]
+"Homepage" = "https://github.com/ivan-sincek/nagooglesearch"
+
+[tool.setuptools.packages.find]
+where = ["src"]

src/nagooglesearch/__init__.py

@@ -0,0 +1,5 @@
+#!/usr/bin/env python3
+
+from .nagooglesearch import get_all_user_agents, get_random_user_agent, get_tbs, GoogleClient
+
+__all__ = ["get_all_user_agents", "get_random_user_agent", "get_tbs", "GoogleClient"]