为什么我得到的是标签列表而不是数字？

Question

import pandas as pd
from bs4 import BeautifulSoup
import numpy as np
import requests
from time import sleep
from random import randint
import re

towns = pd.DataFrame()

url = f"https://www.city-data.com/city/Adak-Alaska.html"
page = requests.get(url).text
doc = BeautifulSoup(page, "html.parser")

sex_population = str(doc.find(id="population-by-sex"))
(males, females) = [float(x) for x in re.findall(r"(?<=\()[0-9]+\.[0-9]+(?=\%\))", sex_population)]
print(males, females)

religion_population = str(doc.find(id="religion"))
atheist = float(re.findall("(?<=None<\/td><td>)[0-9,]*(?=<\/td><td>)", 
religion_population)[0].replace(",", ""))
print(atheist)

total_population = str(doc.find(id="city-population"))
residents = float(re.findall("(?<=</b> )[0-9]*", total_population)[0].replace(",", ""))
print(residents)

believers = re.findall("(<?<td>)[0-9,]*", religion_population)
for x in believers:
    x.replace(",", "")
print(believers)

instead of printing out a list of numbers like I'm expecting, print(believers) prints out a list of < td >. What am I doing wrong here? I checked my work on regex 101.

Answer 1

I would use BeautifulSoup's functions instead of regex - .find_all() , .get_text() ,

import requests
from bs4 import BeautifulSoup

url = "https://www.city-data.com/city/Adak-Alaska.html"
response = requests.get(url)
#print('status:', response.status_code)
soup = BeautifulSoup(response.text, "html.parser")

religion_population = soup.find(id="religion").find_all('tr')

for row in religion_population:
    columns = row.find_all('td')
    if columns:
        religion = columns[0].get_text(strip=True)
        number   = columns[1].get_text(strip=True).replace(",", "")
        print(f'religion: {religion} | number: {number}')

Result:

religion: Orthodox | number: 754
religion: Evangelical Protestant | number: 232
religion: Catholic | number: 185
religion: Other | number: 112
religion: Mainline Protestant | number: 82
religion: None | number: 4196