Python beautifulsoup打印所需的元素

Question

After I find the desired element I have this:

[<div class="statsValue">$1,615,422</div>, <div class="statsValue">1</div>, <div class="statsValue">2</div>]

I would like to get just the number $1,615,422 . How do I do this? I could not find anything useful online.

Here is my code:

from selenium import webdriver
from selenium.webdriver.remote import webelement
import pandas as pd
import time
from bs4 import BeautifulSoup

driver = webdriver.Chrome('chromedriver.exe')
driver.get('https://www.redfin.com/')
search_box = driver.find_element_by_name('searchInputBox')
search_box.send_keys('693 Bluebird Canyon Drive, Laguna Beach, CA 92651')
search_box.submit()
time.sleep(2)

def get_address_url(address):
    url_list = []
    search_box = driver.find_element_by_name('searchInputBox')
    search_box.send_keys('693 Bluebird Canyon Drive, Laguna Beach, CA 92651')
    search_box.submit()
    time.sleep(2)
    url_list.append(driver.current_url)

# element = driver.find_elements_by_class_name('statsValue')
# print(element[0].get_attribute('innerHTML'))

soup = BeautifulSoup(driver.page_source, 'html.parser')
data = soup.find_all(lambda tag: tag.name == 'div' and tag.get('class') == ['statsValue'])

print(data)
print(len(data))
print(type(data))

driver.quit()

Answer 1

You want the text attribute.

data = soup.find_all(lambda tag: tag.name == 'div' and tag.get('class') == ['statsValue'])
for element in data:
    print (element.text)

Answer 2

You can use regex and sub to remove not digits:

import re

price = re.sub("[^0-9]", "", "$1,615,422")
print(price)

Result:

1615422

soup = BeautifulSoup(driver.page_source, 'html.parser')
stats = soup.select(".statsValue")
for s in stats:
    print(s.text)

Answer 3

If you only want to get the number $1,615,422 , I think requests is enough.

hope this code will help you

import requests
from bs4 import BeautifulSoup as Soup

url = 'https://www.redfin.com/CA/Laguna-Beach/693-Bluebird-Canyon-Dr-92651/home/4894466'

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.108 Safari/537.36'
}

r = requests.get(url, headers=headers)

soup = Soup(r.text, 'html5lib')
data = soup.find('div', {'class', 'avm'}).div.text

print(data) # $1,615,422