import gspread_dataframe as gd
import os
from google.colab import drive
from google.colab import files
import gspread
import pandas as pd
from google.colab import auth
auth.authenticate_user()
from oauth2client.client import GoogleCredentials
drive.mount('/content/drive', force_remount=True)
path = "/content/drive/My Drive"
os.chdir(path)
os.listdir(path)
import requests
import lxml
from bs4 import BeautifulSoup
gc = gspread.authorize(GoogleCredentials.get_application_default())
sh = gc.create('stock')
worksheet = gc.open('stock').sheet1
url="https://hk.finance.yahoo.com/quote/0017.HK"
response = requests.get(url)
soup = BeautifulSoup(response.text, "lxml")
head = soup.find_all('span')
h = head[20].getText()
add = soup.find_all('td', class_="Ta(end) Fw(600) Lh(14px)")
new9 = add[4].getText()
new11 = add[5].getText()
d=[]
data = tuple(d.append(da.getText()) for da in head[34:62])
d.insert(9,new9)
d.insert(11,new11)
titles = tuple(d[i] for i in range(0,len(d),2))
print(titles)
worksheet.insert_row(titles, 1)
#print(d)
def getlink():
page_links_list=[]
pages=input("separate with space without comma!\n").split()
for page in pages:
url="https://hk.finance.yahoo.com/quote/"+str(page)+".HK"
page_links_list.append(url)
return page_links_list
for z in getlink():
response = requests.get(z)
soup = BeautifulSoup(response.text, "lxml")
head = soup.find_all('span')
h = head[20].getText()
add = soup.find_all('td', class_="Ta(end) Fw(600) Lh(14px)")
new9 = add[4].getText()
new11 = add[5].getText()
d=[]
titles = tuple(d[i] for i in range(0,len(d),2))
data = tuple(d.append(da.getText()) for da in head[34:62])
d.insert(9,new9)
d.insert(11,new11)
v = tuple(d[i] for i in range(1,len(d),2))
print(v)
worksheet.insert_row(v, 2)
# worksheet.insert_row(titles, 1)
#df = pd.DataFrame({'col name': titles, 'col name1': data}, columns=['col name', 'col name1'])
#gd.set_with_dataframe(worksheet, df)