Merge pull request #7 from shivendrra/dev

pulling new changes from dev

.gitignore

@@ -4,9 +4,12 @@ __pycache__/
 *.py[cod]
 *.exe
 
+*.pypirc
 build
 .vscode
 
+*.egg-info/
+
 # extras
 *.env
 Datasets

README.md

@@ -46,23 +46,23 @@ This library contains some topics, keywords, search queries & channel ids which
 #### Channel Ids
 
 ```python
-from graze.queries import Queries
+from webgraze.queries import Queries
 
 queries = Queries(category="channel")
 ```
 
 #### Search Queries
 
 ```python
-from graze.queries import Queries
+from webgraze.queries import Queries
 
 queries = Queries(category="search")
 ```
 
 #### Image Topics
 
 ```python
-from graze.queries import Queries
+from webgraze.queries import Queries
 
 queries = Queries(category="channel")
 ```
@@ -96,8 +96,8 @@ os.chdir(current_directory)
 
 api_key = os.getenv('yt_key')
 
-from graze import Youtube
-from graze.queries import Queries
+from webgraze import Youtube
+from webgraze.queries import Queries
 
 queries = Queries(category="channel")
 
@@ -112,8 +112,8 @@ The Wikipedia scraper generates target URLs from provided queries, fetches the c
 #### Running the Scraper
 
 ```python
-from graze import Wikipedia
-from graze.queries import Queries
+from webgraze import Wikipedia
+from webgraze.queries import Queries
 
 queries = Queries(category="search")
 wiki = Wikipedia(filepath='../data.txt', metrics=True)
@@ -134,8 +134,8 @@ The Unsplash Image scraper fetches images based on given topics & saves them in
 #### Running the Scraper
 
 ```python
-from graze import Unsplash
-from graze.queries import Queries
+from webgraze import Unsplash
+from webgraze.queries import Queries
 
 topics = Queries("images")
 
@@ -159,8 +159,8 @@ The Britannica scraper generates target URLs from provided queries, fetches the
 #### Running the scraper
 
 ```python
-from graze import Britannica
-from graze.queries import Queries
+from webgraze import Britannica
+from webgraze.queries import Queries
 
 queries = Queries(category="search")
 scraper = Britannica(filepath='../data.txt', metrics=True)
@@ -183,7 +183,7 @@ load_dotenv()
 
 API_KEY = os.getenv("freesound_key")
 
-from graze import Freesound
+from webgraze import Freesound
 
 sound = Freesound(api_key=API_KEY, download_dir="audios", metrics=True)
 sound(topics=["clicks", "background", "nature"])
@@ -220,8 +220,8 @@ Scrapes & downloads pictures from [pexels.com](https://www.pexels.com/) & saves
 #### Running the scraper
 
 ```python
-from graze import Pexels
-from graze.queries import Queries
+from webgraze import Pexels
+from webgraze.queries import Queries
 
 queries = Queries("images")
 scraper = Pexels(directory="./images", metrics=True)

requirements.txt

@@ -1,13 +1,7 @@
 bs4
 requests
 tqdm
-timeit
-json
-re
-googleapiclient
+google-api-python-client
 youtube_transcript_api
-logging
-typing
 selenium
-webdriver-manager
-base64
+webdriver-manager

run.py/run_britannica.py

@@ -2,8 +2,8 @@
 current_directory = os.path.dirname(os.path.abspath(__file__))
 os.chdir(current_directory)
 
-from graze import Britannica
-from graze.queries import Queries
+from webgraze import Britannica
+from webgraze.queries import Queries
 
 queries = Queries(category="search")
 wiki = Britannica(filepath='../data.txt', metrics=True)

run.py/run_freesound.py

@@ -6,7 +6,7 @@
 
 API_KEY = os.getenv("freesound_key")
 
-from graze import Freesound
+from webgraze import Freesound
 
 sound = Freesound(api_key=API_KEY, download_dir="audios", metrics=True)
 sound(topics=["clicks", "background", "nature"])

run.py/run_pexels.py

@@ -1,5 +1,5 @@
-from graze import Pexels
-from graze.queries import Queries
+from webgraze import Pexels
+from webgraze.queries import Queries
 
 queries = Queries("images")
 scraper = Pexels(directory="./images", metrics=True)

run.py/run_transcripts.py

@@ -6,8 +6,8 @@
 
 api_key = os.getenv('yt_key')
 
-from graze import Youtube
-from graze.queries import Queries
+from webgraze import Youtube
+from webgraze.queries import Queries
 
 queries = Queries(category="channel")
 

run.py/run_unsplash.py

@@ -2,8 +2,8 @@
 current_directory = os.path.dirname(os.path.abspath(__file__))
 os.chdir(current_directory)
 
-from graze import Unsplash
-from graze.queries import Queries
+from webgraze import Unsplash
+from webgraze.queries import Queries
 
 topics = Queries("images")
 

run.py/run_wiki.py

@@ -1,5 +1,5 @@
-from graze import Wikipedia
-from graze.queries import Queries
+from webgraze import Wikipedia
+from webgraze.queries import Queries
 
 queries = Queries(category="search")
 wiki = Wikipedia(filepath='../data.txt', metrics=True)

setup.py

@@ -0,0 +1,43 @@
+from setuptools import setup, find_packages
+import codecs
+import os
+
+current_dir = os.path.abspath(os.path.dirname(__file__))
+
+with codecs.open(os.path.join(current_dir, "README.md"), encoding="utf-8") as file:
+  long_description = "\n" + file.read()
+
+VERSION = '1.1.2'
+DESCRIPTION = 'WebScraping library that scrapes & gathers data from multiple sources on the internet'
+
+setup(
+  name="webgraze",
+  version=VERSION,
+  author="shivendra",
+  author_email="shivharsh44@gmail.com",
+  description=DESCRIPTION,
+  long_description=long_description,
+  long_description_content_type="text/markdown",
+  license="MIT",
+  packages=find_packages(),
+  keywords=["webscraping", "scraping", "webscraping library", "web scraping", "python webscraping", "beautifulsoup", "selenium"],
+  classifiers=[
+    "Development Status :: 1 - Planning",
+    "Intended Audience :: Developers",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "License :: OSI Approved :: MIT License",
+  ],
+  install_requires=[
+    "bs4",
+    "tqdm",
+    "google-api-python-client",
+    "requests",
+    "youtube-transcript-api",
+    "selenium",
+    "webdriver-manager",
+  ],
+)

test.py

@@ -1,8 +1,6 @@
-import os
-current_directory = os.path.dirname(os.path.abspath(__file__))
-os.chdir(current_directory)
+from webgraze import Pexels
+from webgraze.queries import Queries
 
-from graze import Freesound
-
-sound = Freesound(api_key="lMKgKjaRmNMZKKxNqkjx", download_dir="audios", metrics=True)
-sound(topics=["clicks", "background", "nature"])
+queries = Queries("images")
+scraper = Pexels(directory="./images", metrics=True)
+scraper(topics=queries())