CODEWITHSUNDEEP
pythonpython-3.xbeautifulsoup
Cookie Monster
Cookie Monster

Reputation: 59

Parse all elements with the same class on Beautiful Soup

I would like to know your advice on how to optimize my code. More precisely, I want to parse all elements with this class 'value-decrease'. Code:

import requests
from bs4 import BeautifulSoup

URL = 'https://finance.i.ua/nbu/'
HEADERS = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/80.0.3987.163 Safari/537.36', 'accept': '*/*'}

def get_html(url, params=None):
    r = requests.get(url, headers=HEADERS, params=params)
    return r

def get_content(html):
    soup = BeautifulSoup(html, 'html.parser')
    items = soup.find_all('div', class_="data_container")
    currency = []
    for item in items:
        currency.append({
            item.find_all('span', class_='value-decrease').get_text(strip=True)
        })
        print(f"1 usd =  {currency} uah")

def parse():
    html = get_html(URL)
    if html.status_code == 200:
        get_content(html.text)
    else:
        print('Error')

parse()

The output should be like this(The numbers are approximate.):

1 usd = 27 uah
1 eur = 29 uah

Upvotes: 1

Views: 220

Answers (2)

Mark Tolonen
Mark Tolonen

Reputation: 178179

currency is a list that grows with each iteration, so it isn't what you want to print. Also value-decrease is value -descrease (extra space). The span is also nested in another span. Here's the fixes:

import requests
from bs4 import BeautifulSoup

URL = 'https://finance.i.ua/nbu/'
HEADERS = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML,like Gecko) Chrome/80.0.3987.163 Safari/537.36', 'accept': '*/*'}

def get_html(url, params=None):
    r = requests.get(url, headers=HEADERS, params=params)
    return r

def get_content(html):
    soup = BeautifulSoup(html, 'html.parser')
    rows = soup.find_all('tr')[1:] # find table rows and throw away header
    for row in rows:
        data = row.find('span',class_='value -decrease') # is the row a decrease?
        if data:
            currency = row.th.get_text().lower()
            value = data.span.get_text()
            print(f'1 {currency} = {value} uah')

def parse():
    html = get_html(URL)
    if html.status_code == 200:
        get_content(html.text)
    else:
        print('Error')

parse()

Output:

1 usd = 27.2022 uah
1 eur = 29.6341 uah

Upvotes: 1

Sri
Sri

Reputation: 2328

I realized the country changes so I updated my code.

def get_content(html):
    soup = BeautifulSoup(html, 'html.parser')
    currency = []
    elems = soup.findAll("span", {"class": "value -decrease"})
    countries = [x.parent.previous_sibling.previous_sibling.get_text(strip=True) for x in elems]
    for i in range(len(elems)):
        cur = elems[i].get_text(strip=True).split('.')[0]
        currency.append(cur)
        print(f"1 {countries[i]} =  {cur} uah")

Upvotes: 0

Related Questions