主页 / 问题 / 1213784
Accepted
Seavegen
Asked:2021-12-04 05:15:34 +0000 UTC2021-12-04 05:15:34 +0000 UTC

bs4 td标签问题

  • 772

如何解析并记录在标签下的表格中td a href？

import requests
from bs4 import BeautifulSoup
import csv

count = 0
headers = {
    "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:83.0) Gecko/20100101 Firefox/83.0"
}

with open("result.csv", "w", encoding='utf-8') as file:
    writer = csv.writer(file)
    writer.writerow(["#", "АДРЕС", "ТЕЛЕФОН", "ВРЕМЯ РАБОТЫ", "КОЛИЧЕСТВО", "ЦЕНА"])
    for num in range(1, 32):
        req = requests.get(f"https://apteka.net.ua/search/availability/6810/page-{num}?region=&city=", headers=headers)
        soup = BeautifulSoup(req.content, 'html.parser')
        for i in soup.find("table").find_all("td"):
            try:
                adress = i.find(class_="col_address").find_all("a")
                for k in adress:
                    adr = k.text

                phones = i.find(class_="col_phone").find_all("a")
                for j in adress:
                    adr = j.text

                work_time = i.find(class_="col_work").text
                quantity = i.find(class_="col_quantity").text
                prices = i.find(class_="quantity").text
                count += 1
            except Exception as e:
                print(e)
                try:
                    writer.writerow([count,adr,phones,work_time,quantity,prices])
                except Exception as e:
                    print(e)

给出错误消息：

'NoneType' object has no attribute 'find_all'
name 'adr' is not defined
python

1 个回答

  1. Best Answer

    我重写了代码，主要问题是您不是逐行解析（也就是说，您必须通过标签tr），而是逐行解析。

    尝试：

    import csv
import time
import traceback

import requests
from bs4 import BeautifulSoup

count = 0
headers = {
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:83.0) Gecko/20100101 Firefox/83.0"
}

with open("result.csv", "w", encoding='utf-8') as file:
    writer = csv.writer(file)
    writer.writerow(["#", "АДРЕС", "ТЕЛЕФОН", "ВРЕМЯ РАБОТЫ", "КОЛИЧЕСТВО", "ЦЕНА"])

    for num in range(1, 32):
        print(f'Parsing #{num}...')
        
        rs = requests.get(f"https://apteka.net.ua/search/availability/6810/page-{num}?region=&city=", headers=headers)
        soup = BeautifulSoup(rs.content, 'html.parser')

        for tr in soup.find("table").select("tbody > tr"):
            # Считаем, что если нет адреса, то нет данных в таблице
            address = tr.select_one('.col_address > a')
            if not address:
                break

            try:
                address = address.text
                phones = tr.select_one('.col_phone > a').text
                work_time = tr.select_one('.col_work').text
                quantity = tr.select_one('.col_quantity').text
                prices = tr.select_one('.quantity').text

                count += 1
                writer.writerow([count, address, phones, work_time, quantity, prices])

            except Exception as e:
                print(f'ERROR. #{num}, tr:\n{tr}\n error: {e}', traceback.format_exc())

        # Чтобы не DOS-ить сайт
        time.sleep(0.2)
    • 2

相关问题