Low Wei Hong lowweihong

Machine Learning | Deep Learning | Data Enthusiast | Kaggler

lowweihong / donwload_file_lxml.py

Created August 31, 2019 08:49

	import lxml.html

	dom = lxml.html.fromstring(r.text)

	for node_link in dom.cssselect('tr > td:nth-child(2) > a:nth-child(3)'):
	url = node_link.get('href') # OR node_link.attrib['href']

	# check whether the url is downloadable
	if is_downloadable(url):
	wget.download(url, './data/' + url.split('&file=')[-1].split('&format')[0] + '.mid')

lowweihong / donwload_file_htmlparser.py

Last active August 31, 2019 09:04

	from html.parser import HTMLParser

	class MyHTMLParser(HTMLParser):
	links = []
	def handle_starttag(self, tag, attrs):
	if tag != 'a':
	return

	for attr in attrs:
	if 'href' in attr[0]:

lowweihong / websocket_crypto.py

Last active September 30, 2023 18:52

	from websocket import create_connection
	import json

	# Copy the web brower header and input as a dictionary
	headers = json.dumps({
	'Accept-Encoding': 'gzip, deflate, br',
	'Accept-Language': 'en-GB,en-US;q=0.9,en;q=0.8',
	'Cache-Control': 'no-cache',
	'Connection': 'Upgrade',
	'Host': 'streamer.cryptocompare.com',

lowweihong / google_feed_news_parser.py

Created April 10, 2020 06:40

	import feedparser
	from pprint import pprint
	from bs4 import BeautifulSoup

	url = "http://news.google.com/news?q=covid-19&hl=en-US&sort=date&gl=US&num=100&output=rss"

	class ParseFeed():

	def __init__(self, url):
	self.feed_url = url

lowweihong / cryptocompare_websocket.py

Last active August 10, 2022 21:51

	from websocket import create_connection
	import json

	# Copy the web brower header and input as a dictionary
	headers = json.dumps({
	'Pragma': 'no-cache',
	'Origin': 'https://www.cryptocompare.com',
	'Accept-Language': 'en-US,en;q=0.9',
	'Sec-WebSocket-Key': 'QknTzkhVwUs8UY+xAE22Kg==',
	'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.54 Safari/537.36',

lowweihong / dummy-movies

Created January 2, 2022 13:04