BeautifulSoup AttributeError
BeautifulSoup AttributeError
提问于 2021-05-25 21:55:30
我正在尝试使用BeautifulSoup和requests抓取谷歌购物。这是我的代码，它非常简单：
from bs4 import BeautifulSoup
import requests
import lxml
import json
def gshop(q):
q = q.replace(' ', '+')
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582"
}
response = requests.get(f'https://www.google.com/search?q={q}&tbm=shop', headers=headers).text
soup = BeautifulSoup(response, 'lxml')
data = []
for container in soup.findAll('div', class_='sh-dgr__content'):
title = container.find('h4', class_='A2sOrd').text
price = container.find('span', class_='a8Pemb').text
supplier = container.find('div', class_='aULzUe IuHnof').text
buy = 'https://google.com'+(container.find('a', class_='eaGTj mQaFGe shntl')['href'])
rating = container.find('span', class_='Rsc7Yb').text
data.append({
"Title": title,
"Price": price,
"Rating": rating,
"Supplier": supplier,
"Link": buy
})
return json.dumps(data, indent = 2, ensure_ascii = False)
print(gshop('toys'))这会抛出一个错误：
Traceback (most recent call last):
File "c:/Users/Maanav/Desktop/ValRal/main.py", line 45, in <module>
print(gshop('toys'))
File "c:/Users/Maanav/Desktop/ValRal/main.py", line 34, in gshop
rating = container.find('span', class_='Rsc7Yb').text
AttributeError: 'NoneType' object has no attribute 'text'请查看一个谷歌购物网址的源代码，以更好地理解我的代码。哪里出了问题？
回答 1
Stack Overflow用户
发布于 2021-05-25 23:10:12
由@simpleApp在评论中解决：
有时，google购物清单上的产品可能没有评级，或者卖家可能没有添加供应商名称。这会使程序停止运行。为了阻止这种情况的发生，我们必须使用异常处理。
from bs4 import BeautifulSoup
import requests
import lxml
import json
def gshop(q):
q = q.replace(' ', '+')
headers = {
"User-Agent":
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.102 Safari/537.36 Edge/18.19582"
}
response = requests.get(f'https://www.google.com/search?q={q}&tbm=shop', headers=headers).text
soup = BeautifulSoup(response, 'lxml')
data = []
for container in soup.findAll('div', class_='sh-dgr__content'):
try:
title = container.find('h4', class_='A2sOrd').text
except:
title = None
try:
price = container.find('span', class_='a8Pemb').text
except:
price = None
try:
supplier = container.find('div', class_='aULzUe IuHnof').text
except:
supplier = None
try:
buy = 'https://google.com'+(container.find('a', class_='eaGTj mQaFGe shntl')['href'])
except:
buy = None
try:
rating = container.find('span', class_='Rsc7Yb').text
except:
rating = None
data.append({
"Title": title,
"Price": price,
"Rating": rating,
"Supplier": supplier,
"Link": buy
})
return json.dumps(data, indent = 2, ensure_ascii = False)页面原文内容由Stack Overflow提供。腾讯云小微IT领域专用引擎提供翻译支持
原文链接：
https://stackoverflow.com/questions/67689486
复制相关文章
相似问题
腾讯云开发者
