使用 Python 匹配 HTML 解析中的输入文本

Question

我认为只设置“text=size”会产生我需要的值。也许我想念理解？我做错了什么？

import requests, re, json, time, sys, os,webbrowser
import subprocess as s
from bs4 import BeautifulSoup as bs
global size

size = "Medium"

'''html  = <option selected="selected" data-sku="51728-003" value="660654030868">Medium - $138.00 USD</option>'''

url = "https://us.octobersveryown.com/collections/shop-all/products/varsity-ovo-polartec-half-zip-pullover-black"

def getStuff():
    print ('')
session = requests.session()
response = session.get(url)
soup = bs(response.text, 'html.parser')
prod_name = soup.find('h1',{'itemprop':'name'}).text
price = soup.find('span',{'id':'ProductPrice'}).text
variant = soup.find(text=size).findPrevious('value').text
#variant ="notworking"
print("\nProd Name: "+prod_name)
print("\nPrice: "+price)
print("\nMatching Variant Value: "+variant)

getStuff()

我的错误是

Traceback (most recent call last):
  File "trythis.py", line 20, in <module>
    variant = soup.find(text=size).findPrevious('value').text
AttributeError: 'NoneType' object has no attribute 'text'

Answer 1

这是一个有趣的问题。由于您正在尝试匹配 option 标记文本中的单词并从该标记获取属性，因此我会执行以下操作：

import requests, re, json, time, sys, os,webbrowser
import subprocess as s
from bs4 import BeautifulSoup as bs
global size

size = "Medium"

html  = """<option selected="selected" data-sku="51728-003" value="660654030868">Medium - $138.00 USD</option>"""

url = "https://us.octobersveryown.com/collections/shop-all/products/varsity-ovo-polartec-half-zip-pullover-black"

def getStuff():
    print ('')
    session = requests.session()
    response = session.get(url)
    soup = bs(response.text, 'html.parser')
    prod_name = soup.find('h1',{'itemprop':'name'}).text
    price = soup.find('span',{'id':'ProductPrice'}).text
    #variant = soup.find(text=size).findPrevious('value').text
    def get_option(size):
        options = soup.find_all('option')
        target_option = [o for o in options if size in o.text][0]
        value = target_option['value']
        return value
    def get_options_and_values():
        option_dic = {}
        options = soup.find_all('option')
        for o in options:
            try:
                option_dic[o.text.split('-')[0].strip()] = int(o['value'])
            except:
                pass
        return option_dic
    print(get_options_and_values())
    print("\nProd Name: "+prod_name)
    print("\nPrice: "+price.strip())
    variant = get_option(size)
    print("\nMatching Variant Value: "+variant)

getStuff()

这给了我：

{'Medium': 660654030868, 'Large': 660654063636}

Prod Name: VARSITY OVO POLARTEC® HALF-ZIP PULLOVER - BLACK

Price: $138.00

Matching Variant Value: 660654030868

这将允许您轻松更改想要获得的大小。这有意义吗？