Python BeautifulSoup：从复杂HTML元素中精准提取数值

<div class="DrugPriceBox__price___dj2lv">₹<!-- -->5</div>

from bs4 import BeautifulSoup

html_doc = '<div class="DrugPriceBox__price___dj2lv">₹<!-- -->5</div>'
soup = BeautifulSoup(html_doc, 'html.parser')

div_tag = soup.find('div', class_='DrugPriceBox__price___dj2lv')
if div_tag:
    print(f"原始文本: {div_tag.text}") # 输出: 原始文本: ₹5
else:
    print("未找到目标div标签。")

import requests

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}
# requests.get(url, headers=headers)

# ... (soup已创建)
element = soup.find('div', class_='some-class')
if element:
    # 安全地访问element.text
    text_content = element.text
else:
    print("目标元素未找到。")

# 尝试查找第一种结构
element1 = soup.find('div', class_='class-A')
if element1:
    price_text = element1.text
else:
    # 如果第一种结构未找到，尝试查找第二种结构
    element2 = soup.find('span', class_='class-B')
    if element2:
        price_text = element2.text
    else:
        price_text = "未找到价格信息"

import string

raw_price_text = "₹5.50" # 假设从element.text获得
acceptable_chars = set(string.digits + '.') # 允许数字和小数点
cleaned_price = ''.join(char for char in raw_price_text if char in acceptable_chars)
print(f"清洗后的价格: {cleaned_price}") # 输出: 清洗后的价格: 5.50

import requests
from bs4 import BeautifulSoup
import string

# 定义请求头，模拟浏览器访问
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
}

def extract_price_from_url(url):
    """
    从指定URL的网页中提取药品价格。
    尝试多种HTML结构并过滤非数字字符。
    """
    try:
        # 发送HTTP请求并检查响应状态
        response = requests.get(url, headers=headers, timeout=10)
        response.raise_for_status()  # 如果状态码不是200，则抛出HTTPError异常
    except requests.exceptions.RequestException as e:
        print(f"请求URL失败: {url}, 错误: {e}")
        return None

    # 使用BeautifulSoup解析HTML内容
    soup = BeautifulSoup(response.content, "html.parser")
    price_text = None

    # 尝试第一种div标签的定价格式
    div_price_box = soup.find('div', class_='DrugPriceBox__price___dj2lv')
    if div_price_box:
        price_text = div_price_box.text
    else:
        # 如果div格式未找到，尝试第二种span标签的定价格式
        # 注意：这里的类名来源于实际网页结构分析
        span_price_box = soup.find('span', class_="PriceBoxPlanOption__margin-right-4___2aqFt PriceBoxPlanOption__stike___pDQVN")
        if span_price_box:
            price_text = span_price_box.text

    if price_text:
        # 过滤非数字字符，只保留数字和小数点，以便转换为浮点数
        acceptable_chars = set(string.digits + '.')
        cleaned_price = ''.join(char for char in price_text if char in acceptable_chars)
        return cleaned_price
    else:
        return "未找到价格"

if __name__ == '__main__':
    # 示例URL，第一个URL对应div格式，第二个对应span格式
    url1 = 'https://www.1mg.com/drugs/acticort-5mg-tablet-321932'
    url2 = 'https://www.1mg.com/drugs/zerodol-sp-tablet-67307'

    print(f"从 {url1} 提取价格:")
    price1 = extract_price_from_url(url1)
    print(f"提取到的价格: {price1}")

    print(f"\n从 {url2} 提取价格:")
    price2 = extract_price_from_url(url2)
    print(f"提取到的价格: {price2}")

    # 假设一个不存在价格信息的页面
    url_no_price = 'https://www.example.com'
    print(f"\n从 {url_no_price} 提取价格:")
    price_no_price = extract_price_from_url(url_no_price)
    print(f"提取到的价格: {price_no_price}")