BeautifulSoup 抓取格式

Question

这是我第一次使用BeautifulSoup，我正试图从当地便利店中删除商店位置数据。

但是，当数据被传递到 CSV 文件时，我在尝试删除空行时遇到了一些问题，我试过 .replace('\n','') 和 .strip() 都没有工作。

此外，我在拆分被抓取并包含在同一个兄弟方法中的数据时遇到问题。

我在下面添加了脚本：

from bs4 import BeautifulSoup
from requests import get
import urllib.request
import sched, time
import csv

url = 'http://www.cheers.com.sg/web/store_location.jsp'

response = get(url)
soup = BeautifulSoup(response.text, 'html.parser')
#print (soup.prettify())

#open a file for writing
location_data = open('data/soupdata.csv', 'w', newline='')

#create the csv writer object
csvwriter = csv.writer(location_data)

cheers = soup.find('div' , id="store_container")

count = 0

#Loop for Header tags
for paragraph in cheers.find_all('b'):

    header1 = paragraph.text.replace(':' , '')
    header2 = paragraph.find_next('b').text.replace(':' , '')
    header3 = paragraph.find_next_siblings('b')[1].text.replace(':' , '')
    if count == 0:      
        csvwriter.writerow([header1, header2, header3])
        count += 1

    break

for paragraph in cheers.find_all('br'): 
    brnext = paragraph.next_sibling.strip()
    brnext1 = paragraph.next_sibling
    test1 = brnext1.next_sibling.next_sibling

    print(test1)
    csvwriter.writerow([brnext, test1])

location_data.close()

生成的输出示例：

输出应该是什么样子的示例：

我怎样才能做到这一点？

提前致谢。

Answer 1

你只需要改变提取地址、电话和营业时间的方式

import csv

from bs4 import BeautifulSoup
from requests import get

url = 'http://www.cheers.com.sg/web/store_location.jsp'

response = get(url)
soup = BeautifulSoup(response.text, 'html.parser')
# print (soup.prettify())

# open a file for writing
location_data = open('data/soupdata.csv', 'w', newline='')

# create the csv writer object
csvwriter = csv.writer(location_data)

cheers = soup.find('div', id="store_container")

count = 0

# Loop for Header tags
for paragraph in cheers.find_all('b'):
    header1 = paragraph.text.replace(':', '')
    header2 = paragraph.find_next('b').text.replace(':', '')
    header3 = paragraph.find_next_siblings('b')[1].text.replace(':', '')
    if count == 0:
        csvwriter.writerow([header1, header2, header3])
        count += 1

    break

for paragraph in cheers.find_all('div'):
    label = paragraph.find_all('b')
    if len(label) == 3:
        print(label)
        address = label[0].next_sibling.next_sibling
        tel = label[1].next_sibling
        hours = label[2].next_sibling
        csvwriter.writerow([address, tel, hours])

location_data.close()

Answer 2

为了使它稍微有条理，你可以尝试如下。我使用了.select() 而不是.find_all()。

import csv
from bs4 import BeautifulSoup
import requests

url = 'http://www.cheers.com.sg/web/store_location.jsp'

response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
with open("output.csv","w",newline="") as infile:
    writer = csv.writer(infile)
    writer.writerow(["Address","Telephone","Store hours"])

    for items in soup.select("#store_container .store_col"): 
        addr = items.select_one("b").next_sibling.next_sibling
        tel = items.select_one("b:nth-of-type(2)").next_sibling
        store = items.select_one("b:nth-of-type(3)").next_sibling
        writer.writerow([addr,tel,store])