对于没有尺寸显示在页面上的产品，如何在csv中输出“无产品尺寸”？（python，网络抓取）

Question

我用python创建了一个网络抓取程序，我想在“产品尺寸”列中显示“无产品尺寸”。这些产品在亚马逊上没有尺寸显示。应该替换的代码在带有尺寸的try catch块上。我附上了程序。我将不胜感激。

这是此程序的输出！我会喜欢从没有产品尺寸的产品尺寸列中更换插件。

from selenium import webdriver
import csv
import io

proxies = {
    'http': 'http://5.189.133.231:80',
    'https': 'https://27.111.43.178:8080'
}

chrome_options = webdriver.ChromeOptions()

chrome_options.add_argument('--proxy-server="%s"' % ';'.join(['%s=%s' % (k, v) for k, v in proxies.items()]))

driver = webdriver.Chrome(executable_path="C:\\Users\Andrei-PC\Downloads\webdriver\chromedriver.exe",
                          chrome_options=chrome_options)
header = ['Product title', 'ASIN', 'Product Weight', 'Product dimensions', 'URL']

with open('csv/products.csv', "w") as output:
    writer = csv.writer(output)
    writer.writerow(header)

links = [
   'https://www.amazon.com/Fermtech-regular-Auto-Siphon-Tubing/dp/B06XMR433X/ref=sr_1_2?s=kitchen&ie=UTF8&qid=1520274561&sr=1-2&keywords=-hhhg',
    'https://www.amazon.com/Hydro-Flask-Wide-Mouth-Flip/dp/B01ACATW7E/ref=sr_1_3?s=kitchen&ie=UTF8&qid=1520348607&sr=1-3&keywords=-gfds',
    'https://www.amazon.com/Cosmetics-Organizer-Compartments-Christmas-birthday/dp/B01BXDDU04/ref=sr_1_4569/138-3260504-2979110?s=bedbath&ie=UTF8&qid=1520585778&sr=1-4569&keywords=-sdfg'
]

for i in range(len(links)):

    driver.get(links[i])

    product_title = driver.find_elements_by_xpath('//*[@id="productTitle"][1]')
    prod_title = [x.text for x in product_title]

    try:
        asin = driver.find_element_by_xpath('(//div[@class ="pdTab"]/table/tbody/tr/td)[24]').text
    except:
        print('no ASIN template one')

    try:
        weight = driver.find_element_by_xpath('(//div[@class ="pdTab"]/table/tbody/tr/td)[2]').text
    except:
        print('no weight template one')

    try:
        dimension = driver.find_element_by_xpath('(//div[@class ="pdTab"]/table/tbody/tr/td)[4]').text
    except:
        print('no dimension template one')

    try:
        asin = driver.find_element_by_xpath('(//table[@id="productDetailsTable"]/tbody/tr/td/div/ul/li)[3]').text
    except:
        print('no ASIN template two')

    try:
        weight = driver.find_element_by_xpath('(//table[@id="productDetailsTable"]/tbody/tr/td/div/ul/li)[3]').text
    except:
        print('no weight template two')
        
    try:
        dimension = driver.find_element_by_xpath('(//table[@id="productDetailsTable"]/tbody/tr/td/div/ul/li)[3]').text
    except:
        print('no dimension template two')

    try:
        asin = driver.find_element_by_xpath('//li[contains(b, "ASIN:")]').text
    except:
        print('no ASIN template three')

    try:
        weight = driver.find_element_by_xpath('//li[contains(b, "Shipping Weight:")]').text
    except:
        print('no weight template three')

    try:
        dimension = driver.find_element_by_xpath('//li[contains(b, "Product Dimensions: ")]').text
    except:
        print('no dimension template three')

    try:
        data = [prod_title[0], asin, weight, dimension, links[i]]
    except:
        print('no data')

    with io.open('csv/products.csv', "a", newline="", encoding="utf-8") as output:
        writer = csv.writer(output)
        writer.writerow(data)

Answer 1

您需要重新排列代码，以便在任何模板中找到ASIN时都不会检查其他模板，因为任何网页都将遵循这三个模板中的任何一个。

jbtw，您的第4，第5和第6个try语句具有相同的代码来提取3个不同的变量。您需要解决该问题。

所以回到您的问题，只需在except块中将维度设置为所需的字符串（即，如果找不到维度）。

try:
    dimension = driver.find_element_by_xpath('//li[contains(b, "Product Dimensions: ")]').text
except:
    dimension = 'NO PRODUCT DIMENSION'

这是重新排列的代码版本（未经测试），但是我敢肯定它会起作用。

for i in range(len(links)):
    asinFound = False
    driver.get(links[i])

    product_title = driver.find_elements_by_xpath('//*[@id="productTitle"][1]')
    prod_title = [x.text for x in product_title]
    if asinFound == False: #try template one
        try:
            asin = driver.find_element_by_xpath('(//div[@class ="pdTab"]/table/tbody/tr/td)[24]').text
            asinFound = True #dont need to try other templates
        except:
            print('no ASIN template one')

        try:
            weight = driver.find_element_by_xpath('(//div[@class ="pdTab"]/table/tbody/tr/td)[2]').text
        except:
            print('no weight template one')

        try:
            dimension = driver.find_element_by_xpath('(//div[@class ="pdTab"]/table/tbody/tr/td)[4]').text
        except:
            dimension = 'No Product Dimension'
            print('no dimension template one')

    if asinFound == False: #try template two
        try:
            asin = driver.find_element_by_xpath('(//table[@id="productDetailsTable"]/tbody/tr/td/div/ul/li)[3]').text
            asinFound = True #dont need to try other templates
        except:
            print('no ASIN template two')

        try:
            weight = driver.find_element_by_xpath('(//table[@id="productDetailsTable"]/tbody/tr/td/div/ul/li)[3]').text
        except:
            print('no weight template two')

        try:
            dimension = driver.find_element_by_xpath('(//table[@id="productDetailsTable"]/tbody/tr/td/div/ul/li)[3]').text
        except:
            dimension = 'No Product Dimension'
            print('no dimension template two')
    if asinFound == False: #try template three
        try:
            asin = driver.find_element_by_xpath('//li[contains(b, "ASIN:")]').text
        except:
            print('no ASIN template three')

        try:
            weight = driver.find_element_by_xpath('//li[contains(b, "Shipping Weight:")]').text
        except:
            print('no weight template three')

        try:
            dimension = driver.find_element_by_xpath('//li[contains(b, "Product Dimensions: ")]').text
        except:
            dimension = 'No Product Dimension'
            print('no dimension template three')

    try:
        data = [prod_title[0], asin, weight, dimension, links[i]]
    except:
        print('no data')

    with io.open('csv/products.csv', "a", newline="", encoding="utf-8") as output:
        writer = csv.writer(output)
        writer.writerow(data)