lowweihong

1
00:01:18,287 --> 00:01:22,212
<i>Get ready for the feel,
the feel of real. X1 .</i>

2
00:01:22,374 --> 00:01:24,126
<i>No pain, no gain.</i>

3

lowweihong

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

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

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

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

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

from bs4 import BeautifulSoup
import wget
soup = BeautifulSoup(r.text, 'lxml')

for node_link in soup.select('tr > td:nth-child(2) > a:nth-child(3)'):
   url = node_link['href']
   if is_downloadable(url):
        wget.download(url,
                      './data/' + url.split('&file=')[-1].split('&format')[0] + '.mid')

lowweihong

from pydrive.auth import GoogleAuth
from pydrive.drive import GoogleDrive
import requests
import pandas as pd
from datetime import datetime, timedelta
from bs4 import BeautifulSoup
import os

def create_folder(drive, folder_name, parent_folder_id):
    """ 

lowweihong

from pydrive.auth import GoogleAuth
from pydrive.drive import GoogleDrive
import requests
import pandas as pd
from datetime import datetime, timedelta
from bs4 import BeautifulSoup
import os

gauth = GoogleAuth()
# Try to load saved client credentials

lowweihong

from pydrive.auth import GoogleAuth
from pydrive.drive import GoogleDrive
import requests
import pandas as pd
from datetime import datetime, timedelta
from bs4 import BeautifulSoup
import os

# Downloading today data from SGX using SGX API
today = datetime.now()