我正在尝试从以下位置抓取数据：-https://www.canadapharmacy.com/
下面是我需要刮的几页：-
https://www.canadapharmacy.com/products/abilify-tablet，
https://www.canadapharmacy.com/products/accolate，
https://www.canadapharmacy.com/products/abilify-mt
我需要从页面的所有信息。我写了下面的代码：-
使用汤：-

base_url = 'https://www.canadapharmacy.com'
data = []
for i in tqdm(range(len(test))):
    r = requests.get(base_url+test[i])
    
    soup = BeautifulSoup(r.text,'lxml')
    # Scraping medicine Name
    try:
        main_name = (soup.find('h1',{"class":"mn"}).text.lstrip()).rstrip()
    except:
        main_name = None
    
    try:
        sec_name = ((soup.find('div',{"class":"product-name"}).find('h3').text.lstrip()).rstrip()).replace('\n','')
    except:
        sec_name = None
    
    try:
        generic_name = (soup.find('div',{"class":"card product generic strength equal"}).find('div').find('h3').text.lstrip()).rstrip()
    except:
        generic_name = None
        
    # Description
    
    card = ''.join([x.get_text(' ',strip=True) for x in soup.select('div.answer.expanded')])

    try:
        des = card.split('Directions')[0].replace('Description','')
    except:
        des = None
    
    try:
        drc = card.split('Directions')[1].split('Ingredients')[0]
    except:
        drc = None
        
    try:
        ingre= card.split('Directions')[1].split('Ingredients')[1].split('Cautions')[0]
    except:
        ingre = None
    
    try:
        cau=card.split('Directions')[1].split('Ingredients')[1].split('Cautions')[1].split('Side Effects')[0]
    except:
        cau = None
    try:
        se= card.split('Directions')[1].split('Ingredients')[1].split('Cautions')[1].split('Side Effects')[1]
    except: 
        se = None

    for j in soup.find('div',{"class":"answer expanded"}).find_all('h4'):
        if 'Product Code' in j.text:
            prod_code = j.text
        
    #prod_code = soup.find('div',{"class":"answer expanded"}).find_all('h4')[5].text #//div[@class='answer expanded']//h4
    
    pharma = {"primary_name":main_name,
            "secondary_name":sec_name,
            "Generic_Name":generic_name,
            'Description':des,
            'Directions':drc,
            'Ingredients':ingre,
            'Cautions':cau,
            'Side Effects':se,
            "Product_Code":prod_code}
    
    data.append(pharma)

使用 selenium ：-

main_name = []
sec_name = []
generic_name = []
strength = []
quantity = []
desc = []
direc = []
ingre = []
cau = []
side_effect = []
prod_code = []

for i in tqdm(range(len(test_url))):
    card = []
    driver.get(base_url+test_url[i])
    time.sleep(1)

    try:
        main_name.append(driver.find_element(By.XPATH,"//div[@class='card product brand strength equal']//h3").text)
    except:
        main_name.append(None)

    try:
        sec_name.append(driver.find_element(By.XPATH,"//div[@class='card product generic strength equal']//h3").text)
    except:
        sec_name.append(None)

    try:
        generic_name.append(driver.find_element(By.XPATH,"//div[@class='card product generic strength equal']//h3").text)
    except:
        generic_name.append(None)

    try:
        for i in driver.find_elements(By.XPATH,"//div[@class='product-content']//div[@class='product-select']//form"):
            strength.append(i.text)

    except:
        strength.append(None)

#     try:
#         for i in driver.find_elements(By.XPATH,"//div[@class='product-select']//form//div[@class='product-select-options'][2]"):
#             quantity.append(i.text)
#     except:
#         quantity.append(None)

    card.append(driver.find_element(By.XPATH,"//div[@class='answer expanded']").text)

    try:
        desc.append(card[0].split('Directions')[0].replace('Description',''))
    except:
        desc.append(None)

    try:
        direc.append(card[0].split('Directions')[1].split('Ingredients')[0])
    except:
        direc.append(None)

    try:
        ingre.append(card[0].split('Directions')[1].split('Ingredients')[1].split('Cautions')[0])
    except:
        ingre.append(None)

    try:
        cau.append(card[0].split('Directions')[1].split('Ingredients')[1].split('Cautions')[1].split('Side Effects')[0])
    except:
        cau.append(None)
    try:
        #side_effect.append(card.split('Directions')[1].split('Ingredients')[1].split('Cautions')[1].split('Side Effects')[1])
        side_effect.append(card[0].split('Cautions')[1].split('Side Effects')[1])
    except: 
        side_effect.append(None)

    for j in driver.find_elements(By.XPATH,"//div[@class='answer expanded']//h4"):
        if 'Product Code' in j.text:
            prod_code.append(j.text)

我可以从页面上刮取数据，但在刮取规格和数量框时遇到了一个问题。我想以这样的方式编写代码，以便我可以分别从每种药物中刮取数据，并将其转换为具有列的数据框，如2mg，5mg，10mg，30片，90片，并显示价格。
我试过这个代码：-

medicine_name1 = []
medicine_name2 = []
strength = []
quantity = []

for i in tqdm(range(len(test_url))):
    driver.get(base_url+test_url[i])
    time.sleep(1)
    
    try:
        name1 = driver.find_element(By.XPATH,"//div[@class='card product brand strength equal']//h3").text
    except:
        name1 = None
        
    try:
        name2 = driver.find_element(By.XPATH,"//div[@class='card product generic strength equal']//h3").text
    except:
        name2 = None
        
    try:
        for i in driver.find_elements(By.XPATH,"//div[@class='product-select']//form//div[@class='product-select-options'][1]"):
            strength.append(i.text)
            medicine_name1.append(name1)
            medicine_name2.append(name2)
    except:
        strength.append(None)
        
    try:
        for i in driver.find_elements(By.XPATH,"//div[@class='product-select']//form//div[@class='product-select-options'][2]"):
            quantity.append(i.text)
    except:
        quantity.append(None)

它工作正常，但仍然，在这里我得到了重复的值为药物。有人可以请检查吗？