0

以下のコードは、各ジムの住所を取得しますが、ジムが開いている時間の出力の間隔にエラーがあります。私が間違っていた場所のアイデアはありますか?

import urlparse

from bs4 import BeautifulSoup
from bs4 import Tag
import requests
import time
import csv

sitemap = 'https://www.planetfitness.com/sitemap'
sitemap_content = requests.get(sitemap).content
soup = BeautifulSoup(sitemap_content, 'html.parser')

atags = soup.select('td[class~=club-title] > a[href^="/gyms"]')
links = [atag.get('href') for atag in atags]

with open('gyms.csv', 'w') as gf:
    gymwriter = csv.writer(gf)
    for link in links:
        gymurl = urlparse.urljoin(sitemap, link)
        sitemap_content = requests.get(gymurl).content
        soup = BeautifulSoup(sitemap_content, 'html.parser')
        gymrow = [ gymurl ]

        address_line1 = soup.select('p[class~=address] > span[class~=address-line1]')
        gymrow.append(address_line1[0].text)
        locality = soup.select('p[class~=address] > span[class~=locality]')
        gymrow.append(locality[0].text)
        administrative_area = soup.select('p[class~=address] > span[class~=administrative-area]')
        gymrow.append(administrative_area[0].text)
        postal_code = soup.select('p[class~=address] > span[class~=postal-code]')
        gymrow.append(postal_code[0].text)
        country = soup.select('p[class~=address] > span[class~=country]')
        gymrow.append(country[0].text)

        strongs = soup.select('div > strong')
        for strong in strongs:
            if strong.text == 'Club Hours':
                for sibling in strong.next_siblings:
                    if isinstance(sibling, Tag):
                        hours = sibling.text
                        gymrow.append(hours)
                        break
        print(gymrow)
        gymwriter.writerow(gymrow)
        time.sleep(3)

ご協力ありがとうございました!

4

2 に答える 2