Odtnhj

I am trying to webscrap ETFs daily information with Python and BeautifulSoup. My code extracts info from Wall Street Journal Page. But I get a max number of retries.
I succesfully scraped 10+ ETFs in one run but now I am trying to scrap new ETFs but I keep getting this proxy error:

ProxyError: HTTPSConnectionPool(host='quotes.wsj.com', port=443): Max
retries exceeded with url: /etf/ACWI (Caused by ProxyError('Cannot
connect to proxy.', error('Tunnel connection failed: 407 Proxy
Authorization Required',)))

I was wondering if there is a way to handle this error. My code is the following:

import requests
from bs4 import BeautifulSoup
import pandas as pd

ticker_list = ["ACWI", "AGG", "EMB", "VTI", "GOVT", "IEMB", "IEMG", "EEM", "PCY", "CWI", "SPY", "EMLC"]
x = len(ticker_list)

date, open_list, previous_list, assets_list, nav_list, shares_list = ( for a in range(6))

for i in range(0,x):
 ticker = ticker_list[i]
 date.append("20181107")
 link = "https://quotes.wsj.com/etf/" + ticker
 proxies = "http":"http://username:password@proxy_ip:proxy_port"
 r = requests.get(link, proxies=proxies)
 #print (r.content)
 html = r.text
 soup = BeautifulSoup(html, "html.parser")

 aux_list, aux_list_2 = ( for b in range(2))

 for data in soup.find_all("ul", attrs="class":"cr_data_collection"):
 for d in data: 
 if d.name == "li":
 aux_list.append(d.text)
 print(d.text) 
 print ("Start List Construction!")
 k = len(aux_list)
 for j in range(0,k):
 auxiliar = 
 if "Volume" in aux_list[j]:
 auxiliar = aux_list[j].split()
 volume = auxiliar[1]
 if "Open" in aux_list[j]:
 auxiliar = aux_list[j].split()
 open_price = auxiliar[1]
 open_list.append(auxiliar[1])
 if "Prior Close" in aux_list[j]:
 auxiliar = aux_list[j].split()
 previous_price = auxiliar[2]
 previous_list.append(auxiliar[2])
 if "Net Assets" in aux_list[j]:
 auxiliar = aux_list[j].split()
 net_assets = auxiliar[2] # In Billions
 assets_list.append(auxiliar[2])
 if "NAV" in aux_list[j]:
 auxiliar = aux_list[j].split()
 nav = auxiliar[1]
 nav_list.append(auxiliar[1])
 if "Shares Outstanding" in aux_list[j]:
 auxiliar = aux_list[j].split()
 shares = auxiliar[2] # In Millions
 shares_list.append(auxiliar[2])

 print ("Open Price: ", open_price, "Previous Price: ", previous_price)
 print ("Net Assets: ", net_assets, "NAV: ", nav, "Shares Outstanding: ", shares)

print nav_list, len(nav_list)
print open_list, len(open_list)
print previous_list, len(previous_list)
print assets_list, len(assets_list)
print shares_list, len(shares_list)

data = "Fecha": date, "Ticker": ticker_list, "NAV": nav_list, "Previous Close": previous_list, "Open Price": open_list, "Net Assets (Bn)": assets_list, "Shares (Mill)": shares_list
df = pd.DataFrame(data, columns = ["Fecha", "Ticker", "Net Assets", "Previous Close", "Open Price", "NAV", "Shares"])
df

df.to_excel("C:\Users\labnrodriguez\Documents\out_WSJ.xlsx", sheet_name="ETFs", header = True, index = False) #, startrow = rows)

The output is the following table in a Excel file:

You don't need to scrape their data in the first place. The etfdb-api Node.js package provides you with ETF data:

• Ticker


• Assets under Management


• Open Price


• Avg. Volumne


• etc.

See my post here: https://stackoverflow.com/a/53859924/9986657