Buy fast & affordable proxy servers. Get 10 proxies today for free.
Download our Proxy Server Extension
Products
© Webshare Proxy
payment methods
TL;DR
Google Finance is one of the most trusted platforms for tracking live stock performance, financial statements, and market trends across global exchanges. In this guide, you’ll learn how to build a Google Finance web scraper in Python that collects structured data for a list of stock tickers.
Before building and running the Google Finance scraper, ensure that your environment is correctly configured with all the necessary tools and dependencies.
python --versionpip install playwrightThe below libraries come pre-installed with Python but make sure they are available:
playwright install chromiumFollow the steps below to build and run your Google Finance scraper that collects stock data, company details, financials, and news for multiple tickers.
Start by defining the stock tickers you want to scrape. Use the format SYMBOL:EXCHANGE and separate each ticker with a semicolon. Example:
AMZN:NASDAQ; TSLA:NASDAQ; VOW:ETRIn the company overview area, gather important background information including:
This provides essential company context alongside financial data.
For every ticker, store the collected information in a single structured object that includes:
Note: This code uses await main() which works in Google Colab and Jupyter notebooks. For regular Python scripts, use this instead:
if __name__ == "__main__":
asyncio.run(main())Here’s the complete code:
import asyncio
from playwright.async_api import async_playwright
import json
import sys
class GoogleFinanceScraper:
def __init__(self):
self.base_url = "https://www.google.com/finance"
self.proxy_url = 'http://p.webshare.io:80'
self.proxy_username = 'your_username-rotate'
self.proxy_password = 'your_password'
async def setup_browser(self):
playwright = await async_playwright().start()
browser = await playwright.chromium.launch(
headless=True,
args=['--no-sandbox', '--disable-setuid-sandbox']
)
context = await browser.new_context(
viewport={'width': 1920, 'height': 1080},
user_agent='Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
proxy={
'server': self.proxy_url,
'username': self.proxy_username,
'password': self.proxy_password
}
)
page = await context.new_page()
return playwright, browser, page
async def scrape_ticker(self, ticker):
playwright, browser, page = await self.setup_browser()
try:
url = f"{self.base_url}/quote/{ticker}"
response = await page.goto(url, timeout=30000, wait_until='domcontentloaded')
await page.wait_for_timeout(5000)
data = {
"ticker": ticker,
"company_name": "",
"current_price": "",
"price_change": "",
"price_change_amount": "",
"market_status": "",
"overview_stats": {},
"financials": {
"income_statement": [],
"balance_sheet": [],
"cash_flow": []
},
"news": [],
"about": {}
}
await self.scrape_basic_info(page, data)
await self.scrape_financials(page, data)
return data
except Exception as e:
return None
finally:
await browser.close()
await playwright.stop()
async def scrape_basic_info(self, page, data):
company_el = await page.query_selector('.zzDege')
if company_el:
data["company_name"] = (await company_el.text_content() or "").strip()
price_selectors = [
'.YMlKec.fxKbKc',
'.fxKbKc',
'.YMlKec',
'[data-field="regularMarketPrice"]',
'.AHmHk'
]
for selector in price_selectors:
price_el = await page.query_selector(selector)
if price_el:
price_text = (await price_el.text_content() or "").strip()
if price_text and '$' in price_text and len(price_text) < 20:
data["current_price"] = price_text
break
change_el = await page.query_selector('.JwB6zf')
if change_el:
data["price_change"] = (await change_el.text_content() or "").strip()
change_amt_el = await page.query_selector('.BAftM')
if change_amt_el:
data["price_change_amount"] = (await change_amt_el.text_content() or "").strip()
status_el = await page.query_selector('.exOpGd')
if status_el:
data["market_status"] = (await status_el.text_content() or "").strip()
await self.scrape_overview_stats(page, data)
await self.scrape_news(page, data)
await self.scrape_about_section(page, data)
async def scrape_overview_stats(self, page, data):
try:
stat_labels = await page.query_selector_all('.mfs7Fc')
stat_values = await page.query_selector_all('.P6K39c')
if stat_labels and stat_values:
for i, (label_el, value_el) in enumerate(zip(stat_labels, stat_values)):
if i < len(stat_values):
label = (await label_el.text_content() or "").strip()
value = (await value_el.text_content() or "").strip()
if label and value:
clean_label = label.lower().replace(' ', '_').replace('.', '').replace('-', '_')
data["overview_stats"][clean_label] = value
except Exception as e:
pass
async def scrape_news(self, page, data):
try:
news_elements = await page.query_selector_all('.yY3Lee')
for news_el in news_elements[:6]:
news_data = {}
headline_el = await news_el.query_selector('.Yfwt5')
if headline_el:
news_data["headline"] = (await headline_el.text_content() or "").strip()
source_el = await news_el.query_selector('.sfyJob')
if source_el:
news_data["source"] = (await source_el.text_content() or "").strip()
link_el = await news_el.query_selector('a')
if link_el:
news_data["link"] = await link_el.get_attribute('href') or ""
if news_data:
data["news"].append(news_data)
except Exception as e:
pass
async def scrape_about_section(self, page, data):
try:
about_text_el = await page.query_selector('.bLLb2d')
if about_text_el:
about_text = (await about_text_el.text_content() or "").strip()
if about_text:
data["about"]["description"] = about_text
about_items = await page.query_selector_all('.LuLFhc')
for item in about_items:
label_el = await item.query_selector('.OspXqd')
value_el = await item.query_selector('.oJCxTc')
if label_el and value_el:
label = (await label_el.text_content() or "").strip()
value = (await value_el.text_content() or "").strip()
if label == "CEO":
data["about"]["ceo"] = value
elif label == "Headquarters":
data["about"]["headquarters"] = value
elif label == "Employees":
data["about"]["employees"] = value
elif label == "Sector":
data["about"]["sector"] = value
elif label == "Founded":
data["about"]["founded"] = value
elif label == "Website":
data["about"]["website"] = value
except Exception as e:
pass
async def scrape_financials(self, page, data):
"""Scrape all financial statements by expanding and navigating through sections"""
# First, try to find and expand the Income Statement section
await self.expand_financial_section(page, "Income Statement")
# Scrape income statement
await self.scrape_income_statement(page, data)
# Find and expand Balance Sheet section
balance_sheet_expanded = await self.expand_financial_section(page, "Balance Sheet")
if balance_sheet_expanded:
await page.wait_for_timeout(2000)
await self.scrape_balance_sheet(page, data)
# Find and expand Cash Flow section
cash_flow_expanded = await self.expand_financial_section(page, "Cash Flow")
if cash_flow_expanded:
await page.wait_for_timeout(2000)
await self.scrape_cash_flow(page, data)
async def expand_financial_section(self, page, section_name):
"""Find and click to expand a financial section"""
try:
# Look for expandable sections with the specific section name
section_selectors = [
f'div[role="button"]:has-text("{section_name}")',
f'button:has-text("{section_name}")',
f'.oX8Xbb:has-text("{section_name}")',
f'[jsname="HSrbLb"]:has-text("{section_name}")',
f'.ECi4Zd:has-text("{section_name}")'
]
for selector in section_selectors:
section_element = await page.query_selector(selector)
if section_element:
# Check if section is already expanded
aria_expanded = await section_element.get_attribute('aria-expanded')
if aria_expanded != 'true':
await section_element.click()
await page.wait_for_timeout(2000)
return True
return False
except Exception as e:
return False
async def scrape_table_data(self, table, data_list):
"""Generic method to scrape data from financial tables"""
try:
rows = await table.query_selector_all('tr.roXhBd')
if not rows:
return
for row in rows:
cells = await row.query_selector_all('td, th')
if len(cells) >= 3:
row_data = {}
label_cell = cells[0]
label_el = await label_cell.query_selector('.rsPbEe')
if label_el:
row_data["item"] = (await label_el.text_content() or "").strip()
value_cell = cells[1]
if value_cell:
row_data["value"] = (await value_cell.text_content() or "").strip()
change_cell = cells[2]
if change_cell:
row_data["yoy_change"] = (await change_cell.text_content() or "").strip()
if "item" in row_data and row_data["item"]:
data_list.append(row_data)
except Exception as e:
pass
async def scrape_income_statement(self, page, data):
try:
# Look for income statement table within the Income Statement section
income_section = await page.query_selector('.ECi4Zd:has-text("Income Statement")')
if income_section:
income_table = await income_section.query_selector('table.slpEwd')
if income_table:
await self.scrape_table_data(income_table, data["financials"]["income_statement"])
except Exception as e:
pass
async def scrape_balance_sheet(self, page, data):
try:
# Look for balance sheet table within the Balance Sheet section
balance_section = await page.query_selector('.ECi4Zd:has-text("Balance Sheet")')
if balance_section:
balance_table = await balance_section.query_selector('table.slpEwd')
if balance_table:
await self.scrape_table_data(balance_table, data["financials"]["balance_sheet"])
except Exception as e:
pass
async def scrape_cash_flow(self, page, data):
try:
# Look for cash flow table within the Cash Flow section
cash_flow_section = await page.query_selector('.ECi4Zd:has-text("Cash Flow")')
if cash_flow_section:
cashflow_table = await cash_flow_section.query_selector('table.slpEwd')
if cashflow_table:
await self.scrape_table_data(cashflow_table, data["financials"]["cash_flow"])
except Exception as e:
pass
async def main():
# Configure a list of tickers to scrape
tickers_input = "AMZN:NASDAQ; TSLA:NASDAQ; VOW:ETR"
tickers = [ticker.strip() for ticker in tickers_input.split(';')]
print(f"Scraping data for tickers: {', '.join(tickers)}")
scraper = GoogleFinanceScraper()
all_data = []
for ticker in tickers:
print(f"Scraping {ticker}...")
ticker_data = await scraper.scrape_ticker(ticker)
if ticker_data:
all_data.append(ticker_data)
print(f"Successfully scraped {ticker}")
else:
print(f"Failed to scrape {ticker}")
await asyncio.sleep(3)
if all_data:
with open('google_finance_data.json', 'w', encoding='utf-8') as f:
json.dump(all_data, f, indent=2, ensure_ascii=False)
print(f"Data saved to google_finance_data.json for {len(all_data)} tickers")
else:
print("No data was scraped.")
await main()Here’s the output:
The generated json is as:
In this article, we built a Google Finance scraper using Playwright and Webshare rotating residential proxies to reliably extract structured financial data from dynamically rendered pages. The scraper collects detailed information for any list of stock tickers – including current prices, market stats, company details, recent news, and full financial statements (income statement, balance sheet, and cash flow).
