get the href link in table columns in python with -beautiful-soup-CodePudding

I have this data as you can see :

[<td><span></span></td>, <td><span></span></td>, <td><a class="cmc-link" href="/currencies/renbtc/"><span class="circle"></span><span>renBTC</span><span class="crypto-symbol">RENBTC</span></a></td>, <td><span>$<!-- -->61947.68</span></td>, <td><span></span></td>]

I want to extract the href link as you can see here is /currencies/renbtc/.

Here is my code:

from bs4 import BeautifulSoup
import requests
try:
    r = requests.get('https://coinmarketcap.com/')
    soup = BeautifulSoup(r.text, 'lxml')

    
    table = soup.find('table', class_='cmc-table')
    for row in table.tbody.find_all('tr'):    
        # Find all data for each column
         columns = row.find_all('td')
         print(columns)
         
except requests.exceptions.RequestException as e:
    print(e)

but the result is the whole columns .

CodePudding user response：

Iterate over the <td> in the list and if that <td> has <a> (if td.a), then .get('href') of td.a:

from bs4 import BeautifulSoup
import requests
try:
    r = requests.get('https://coinmarketcap.com/')
    soup = BeautifulSoup(r.text, 'lxml')

    table = soup.find('table', class_='cmc-table')

    for row in table.tbody.find_all('tr'):
        # Find all data for each column
        columns = row.find_all('td')
        for td in columns:
            if td.a:
                print(td.a.get('href'))
                # theoretically for performance you can
                # break
                # here to stop the loop if you expect only one anchor link per `td`

except requests.exceptions.RequestException as e:
    print(e)

CodePudding user response：

Operate on the element from columns that holds the <a>, select it and get its href:

link = columns[2].a['href']

Example

from bs4 import BeautifulSoup
import requests
try:
    r = requests.get('https://coinmarketcap.com/')
    soup = BeautifulSoup(r.text, 'lxml')

    
    table = soup.find('table', class_='cmc-table')
    for row in table.tbody.find_all('tr'):    
        # Find all data for each column
         columns = row.find_all('td')
         link = columns[2].a['href']
         print(link)
         
except requests.exceptions.RequestException as e:
    print(e)