from bs4 import BeautifulSoup
import requests

url = 'https://en.wikipedia.org/wiki/List_of_largest_companies_by_revenue'
page = requests.get(url)


soup = BeautifulSoup(page.text, 'html')


print(soup)

soup.find_all('table')




soup.find('table', class_ = 'wikitable sortable ')




table = soup.find_all('table')[1]

print(table)

world_titles = table.find_all('th')

world_titles

world_table_titles = [title.text.strip() for title in world_titles]
print ( world_table_titles)

import pandas as pd

df = pd.DataFrame(columns = world_table_titles)
df

column_data = table.find_all('tr')

for row in column_data[2:]: #baştaki boşluk gitti
    row_data = row.find_all('td')
    individual_row_Data = [data.text.strip() for data in row_data]
    lenght = len(df)
    df.loc[lenght] == individual_row_Data

df

import numpy as np
import pandas as pd
pd.set_option('display.expand_frame_repr', False)

df = pd.read_html('https://en.wikipedia.org/wiki/List_of_largest_companies_by_revenue')[0]
df.columns = df.columns.get_level_values(1)
df.columns = ['Rank', 'Name', 'Industry', 'Revenue', 'Profit', 'Employees', 'Headquarters[note 1]', 'State-owned', 'Ref.'] 

>>> df.head()
   Rank                             Name     Industry   Revenue    Profit  Employees Headquarters[note 1]  State-owned    Ref.
0     1                          Walmart       Retail  $611,289   $11,680    2100000        United States          NaN     [1]
1     2                     Saudi Aramco  Oil and gas  $603,651  $159,069      70496         Saudi Arabia          NaN     [4]
2     3  State Grid Corporation of China  Electricity  $530,009    $8,192     870287                China          NaN     [5]
3     4                 Amazon.com, Inc.       Retail  $513,983   −$2,722    1541000        United States          NaN     [6]
4     5                            Vitol  Commodities  $505,000   $15,000       1560          Switzerland          NaN  [7][8]

# look a Types
>>> df.dtypes
Rank                      int64
Name                     object
Industry                 object
Revenue                  object
Profit                   object
Employees                 int64
Headquarters[note 1]     object
State-owned             float64
Ref.                     object

# Fix Types
dtype: object
>>> df['Revenue'] = df['Revenue'].str.replace('[\$,]', '', regex=True).astype(float)
>>> df['Profit'] = df['Profit'].str.replace('[^\d.-]', '', regex=True)
>>> df['Profit'].replace('...', np.nan, inplace=True)
>>> df['Profit'] = df['Profit'].astype(float)

# Types ok
>>> df.dtypes
Rank                      int64
Name                     object
Industry                 object
Revenue                 float64
Profit                  float64
Employees                 int64
Headquarters[note 1]     object
State-owned             float64
Ref.                     object

>>> df['Revenue'].max()
611289.0

>>> df.loc[df['Revenue'].idxmax()]
Rank                                1
Name                          Walmart
Industry                       Retail
Revenue                      611289.0
Profit                        11680.0
Employees                     2100000
Headquarters[note 1]    United States
State-owned                       NaN
Ref.                              [1]
Name: 0, dtype: object

Quote:Financial Statement and Notes Data Sets
The data sets provide the text and detailed numeric information in all financial statements and their notes extracted from exhibits to corporate financial reports filed with the Commission using eXtensible Business Reporting Language (XBRL).
Updated Aug. 2023

(Sep-21-2023, 04:16 PM)snippsat Wrote: df.loc[df['Revenue'].idxmax()]