├── .gitignore ├── LICENSE ├── README.md ├── aljazeera ├── demo.py ├── html │ ├── aj.html │ └── simplenews.html └── lib │ ├── aljazeera.py │ ├── helper.py │ └── log.py ├── basics ├── 1.connection.py └── 2.beautifulsoup.py ├── quotes ├── Pipfile ├── Pipfile.lock ├── README.md └── quotes │ ├── azinfo.html │ ├── quotes │ ├── __init__.py │ ├── items.py │ ├── middlewares.py │ ├── pipelines.py │ ├── settings.py │ └── spiders │ │ ├── __init__.py │ │ └── quotes_spider.py │ └── scrapy.cfg └── selenium ├── README.md ├── chromedriver └── demo.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/README.md -------------------------------------------------------------------------------- /aljazeera/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/aljazeera/demo.py -------------------------------------------------------------------------------- /aljazeera/html/aj.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/aljazeera/html/aj.html -------------------------------------------------------------------------------- /aljazeera/html/simplenews.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/aljazeera/html/simplenews.html -------------------------------------------------------------------------------- /aljazeera/lib/aljazeera.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/aljazeera/lib/aljazeera.py -------------------------------------------------------------------------------- /aljazeera/lib/helper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/aljazeera/lib/helper.py -------------------------------------------------------------------------------- /aljazeera/lib/log.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/aljazeera/lib/log.py -------------------------------------------------------------------------------- /basics/1.connection.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/basics/1.connection.py -------------------------------------------------------------------------------- /basics/2.beautifulsoup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/basics/2.beautifulsoup.py -------------------------------------------------------------------------------- /quotes/Pipfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/Pipfile -------------------------------------------------------------------------------- /quotes/Pipfile.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/Pipfile.lock -------------------------------------------------------------------------------- /quotes/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/README.md -------------------------------------------------------------------------------- /quotes/quotes/azinfo.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/quotes/azinfo.html -------------------------------------------------------------------------------- /quotes/quotes/quotes/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /quotes/quotes/quotes/items.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/quotes/quotes/items.py -------------------------------------------------------------------------------- /quotes/quotes/quotes/middlewares.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/quotes/quotes/middlewares.py -------------------------------------------------------------------------------- /quotes/quotes/quotes/pipelines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/quotes/quotes/pipelines.py -------------------------------------------------------------------------------- /quotes/quotes/quotes/settings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/quotes/quotes/settings.py -------------------------------------------------------------------------------- /quotes/quotes/quotes/spiders/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/quotes/quotes/spiders/__init__.py -------------------------------------------------------------------------------- /quotes/quotes/quotes/spiders/quotes_spider.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/quotes/quotes/spiders/quotes_spider.py -------------------------------------------------------------------------------- /quotes/quotes/scrapy.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/quotes/quotes/scrapy.cfg -------------------------------------------------------------------------------- /selenium/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/selenium/README.md -------------------------------------------------------------------------------- /selenium/chromedriver: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/selenium/chromedriver -------------------------------------------------------------------------------- /selenium/demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/mahmudahsan/webscraping/HEAD/selenium/demo.py --------------------------------------------------------------------------------