问题

adress = company.find_all('span')[1].text + company.find_all('span')[2].text + company.find_all('span')[3].text + company.find_all('span')[4].text

`from bs4 import BeautifulSoup
import requests, openpyxl

#excel =  openpyxl.Workbook()
#print(excel.sheetnames)
#sheet = excel.active
#sheet.title = 'KNX manufacturers'
#print(excel.sheetnames)
#sheet.append(['name', 'description', 'country', 'website', 'phone', 'CEO', 'adress'])

try:
	source = requests.get('https://www.knx.org/knx-en/for-professionals/community/manufacturers/')
	source.raise_for_status()

	soup = BeautifulSoup(source.text,'html.parser')

	companys = soup.find('div', class_="accordion").find_all('li')
	
	for company in companys:

		name = company.find('span', class_="desktop_only").text

		description = company.find('div', class_="col-md-6 col-sm-12 col-xs-12").text.strip()

		country = company.find('div', class_="col-lg-4 col-sm-6 col-xs-6 item").span.text

		website = company.find('div', class_="col-sm-6 col-xs-12").a.text

		phone = company.find('div', class_="col-sm-6 col-xs-12").find_all('span')[5].text.strip('Phone: ')

		CEO = company.find('div', class_="col-sm-6 col-xs-12").find_all('strong')[0].text.strip()

		adress = company.find('div', class_="col-sm-6 col-xs-12").find_all('span')[1, 2, 3, 4].text

		print(adress)
		#print(name, description, country, website, phone, CEO, adress)
		#sheet.append([name, description, country, website, phone, CEO, adress])
		break

except Exception as e:
	print(e)

#excel.save('KNX manufacturers | Bemsiq.xlsx')`

答案1

得分: 1

要将所有数据从表格提取到pandas DataFrame中，您可以尝试：

```py
import re
import requests
import pandas as pd
from bs4 import BeautifulSoup


url = 'https://www.knx.org/knx-en/for-professionals/community/manufacturers/'

soup = BeautifulSoup(requests.get(url).content, 'html.parser')

def get_text(tag):
    return re.sub(r'\s{2,}', ' ', tag.text.strip())

all_data = []
for a in soup.select('.accordion-body'):
    name = a.select_one('.mobile_only').text
    phone = a.select_one('strong:-soup-contains("Phone:")')
    phone = phone.find_next_sibling(string=True) if phone else '-'

    web = a.select_one('strong:-soup-contains("Website:") + a')
    web = web['href'] if web else '-'

    email = a.select_one('strong:-soup-contains("Email:") + a')
    email = email['href'] if email else '-'

    person = a.strong
    line1 = person.find_next_sibling("span")
    line2 = line1.find_next_sibling("span")
    line3 = line2.find_next_sibling("span")

    address = f'{get_text(line1)}, {get_text(line2)}, {get_text(line3)}'
    person = person.text

    all_data.append((name, phone, web, email, person, address))


df = pd.DataFrame(all_data, columns=['Name', 'Phone', 'Web', 'Email', 'Person', 'Address'])
print(df.head(10).to_markdown(index=False))

打印结果：

<details>
<summary>英文:</summary>

To get all data from the table to pandas DataFrame you can try:

```py
import re
import requests
import pandas as pd
from bs4 import BeautifulSoup


url = &#39;https://www.knx.org/knx-en/for-professionals/community/manufacturers/&#39;

soup = BeautifulSoup(requests.get(url).content, &#39;html.parser&#39;)

def get_text(tag):
    return re.sub(r&#39;\s{2,}&#39;, &#39; &#39;, tag.text.strip())

all_data = []
for a in soup.select(&#39;.accordion-body&#39;):
    name = a.select_one(&#39;.mobile_only&#39;).text
    phone = a.select_one(&#39;strong:-soup-contains(&quot;Phone:&quot;)&#39;)
    phone = phone.find_next_sibling(string=True) if phone else &#39;-&#39;

    web = a.select_one(&#39;strong:-soup-contains(&quot;Website:&quot;) + a&#39;)
    web = web[&#39;href&#39;] if web else &#39;-&#39;

    email = a.select_one(&#39;strong:-soup-contains(&quot;Email:&quot;) + a&#39;)
    email = email[&#39;href&#39;] if email else &#39;-&#39;

    person = a.strong
    line1 = person.find_next_sibling(&quot;span&quot;)
    line2 = line1.find_next_sibling(&quot;span&quot;)
    line3 = line2.find_next_sibling(&quot;span&quot;)

    address = f&#39;{get_text(line1)}, {get_text(line2)}, {get_text(line3)}&#39;
    person = person.text

    all_data.append((name, phone, web, email, person, address))


df = pd.DataFrame(all_data, columns=[&#39;Name&#39;, &#39;Phone&#39;, &#39;Web&#39;, &#39;Email&#39;, &#39;Person&#39;, &#39;Address&#39;])
print(df.head(10).to_markdown(index=False))

Prints:

答案2

得分: 0

错误的原因是您不能直接将索引列表传递给find_all()，如您尝试的那样。相反，您应该使用列表推导或单独的find_all()调用来提取不同标签的结果，然后将它们连接成一个单一的字符串。

以下是如何修改您的代码以实现这一点：

from bs4 import BeautifulSoup
import requests

try:
    source = requests.get('https://www.knx.org/knx-en/for-professionals/community/manufacturers/')
    source.raise_for_status()

    soup = BeautifulSoup(source.text, 'html.parser')

    companies = soup.find('div', class_='accordion').find_all('li')

    for company in companies:

        name = company.find('span', class_='desktop_only').text
        description = company.find('div', class_='col-md-6 col-sm-12 col-xs-12').text.strip()
        country = company.find('div', class_='col-lg-4 col-sm-6 col-xs-6 item').span.text
        website = company.find('div', class_='col-sm-6 col-xs-12').a.text
        phone = company.find('div', class_='col-sm-6 col-xs-12').find_all('span')[5].text.strip('Phone: ')
        CEO = company.find('div', class_='col-sm-6 col-xs-12').find_all('strong')[0].text.strip()

        # 将地址组件单独提取出来
        address_parts = company.find('div', class_='col-sm-6 col-xs-12').find_all('span')[1:5]
        address = ', '.join(part.text for part in address_parts)

        print(address)
        # 进行进一步处理或保存到Excel
        break

except Exception as e:
    print(e)

通过这种修改，地址组件（span元素1到4）将被单独提取，然后使用', ' .join()连接在一起，创建一个包含所有地址部分的单一地址字符串。

现在您应该可以看到每家公司的完整地址打印出来，并可以根据需要进行进一步处理或保存到Excel文件。

from bs4 import BeautifulSoup
import requests

try:
    source = requests.get('https://www.knx.org/knx-en/for-professionals/community/manufacturers/')
    source.raise_for_status()

    soup = BeautifulSoup(source.text,'html.parser')

    companys = soup.find('div', class_="accordion").find_all('li')
    
    for company in companys:

        name = company.find('span', class_="desktop_only").text
        description = company.find('div', class_="col-md-6 col-sm-12 col-xs-12").text.strip()
        country = company.find('div', class_="col-lg-4 col-sm-6 col-xs-6 item").span.text
        website = company.find('div', class_="col-sm-6 col-xs-12").a.text
        phone = company.find('div', class_="col-sm-6 col-xs-12").find_all('span')[5].text.strip('Phone: ')
        CEO = company.find('div', class_="col-sm-6 col-xs-12").find_all('strong')[0].text.strip()

        # Extract the address components separately
        address_parts = company.find('div', class_="col-sm-6 col-xs-12").find_all('span')[1:5]
        address = ', '.join(part.text for part in address_parts)

        print(address)
        # Do further processing or saving to Excel
        break

except Exception as e:
    print(e)