How to scrape data other then stock data from yahoo finance

Question

I'm wanting to scrape data on different shoe companies. I am trying to scrape the EPS from yahoo-finance however I cant find anywhere how to do this. The only way I see so far is finding stock data as open,close etc. How can I scrape data from yahoo-fiance that is not stock data.

Answer 1

This will grab the metrics you want and write everything to a CSV file.

import csv
import requests
from bs4 import BeautifulSoup

url_base = "https://finviz.com/quote.ashx?t="
tckr = ['SBUX','MSFT','AAPL']
url_list = [url_base + s for s in tckr]

with open('C:/your_path_here/metrics.csv', 'a', newline='') as f:
    writer = csv.writer(f)

    for url in url_list:
        try:
            fpage = requests.get(url)
            fsoup = BeautifulSoup(fpage.content, 'html.parser')

            # write header row
            writer.writerow(map(lambda e : e.text, fsoup.find_all('td', {'class':'snapshot-td2-cp'})))

            # write body row
            writer.writerow(map(lambda e : e.text, fsoup.find_all('td', {'class':'snapshot-td2'})))            
        except HTTPError:
            print("{} - not found".format(url))

Answer 2

Here is another approach for you. Notice: by changing the URL, you can or delete different metrics to download.

import requests
from bs4 import BeautifulSoup

base_url = 'http://finviz.com/screener.ashx?v=152&s=ta_topgainers&o=price&c=0,1,2,3,4,5,6,7,25,63,64,65,66,67'
html = requests.get(base_url)
soup = BeautifulSoup(html.content, "html.parser")
main_div = soup.find('div', attrs = {'id':'screener-content'})

light_rows = main_div.find_all('tr', class_="table-light-row-cp")
dark_rows = main_div.find_all('tr', class_="table-dark-row-cp")

data = []
for rows_set in (light_rows, dark_rows):
    for row in rows_set:
        row_data = []
        for cell in row.find_all('td'):
            val = cell.a.get_text()
            row_data.append(val)
        data.append(row_data)

#   sort rows to maintain original order
data.sort(key=lambda x: int(x[0]))
import pandas
pandas.DataFrame(data).to_csv("C:/Users/ryans/OneDrive/Desktop/today.csv", header=False)