Beautifuuloup找不到标签

Question

im正在从事beautifulsoup 项目

from bs4 import BeautifulSoup as soup
from requests import get

url = "https://www.yelp.com/search?find_desc=&find_loc=New+York%2C+NY&ns=1"
clnt = get(url)
page=soup(clnt.text,"html.parser")
container = page.findAll("div",{"class":"lemon--div__373c0__1mboc container__373c0__ZB8u4 hoverable__373c0__3CcYQ margin-t3__373c0__1l90z margin-b3__373c0__q1DuY padding-t3__373c0__1gw9E padding-r3__373c0__57InZ padding-b3__373c0__342DA padding-l3__373c0__1scQ0 border--top__373c0__3gXLy border--right__373c0__1n3Iv border--bottom__373c0__3qNtD border--left__373c0__d1B7K border-color--default__373c0__3-ifU"})
container = container[1]
url2= "https://www.yelp.com"+container.a["href"]
clnt2 = get(url2)
page2 = soup(clnt2.text, 'html.parser')
info = page2.find("div",{"class":"lemon--div__373c0__1mboc island__373c0__3fs6U u-padding-t1 u-padding-r1 u-padding-b1 u-padding-l1 border--top__373c0__19Owr border--right__373c0__22AHO border--bottom__373c0__uPbXS border--left__373c0__1SjJs border-color--default__373c0__2oFDT background-color--white__373c0__GVEnp"})
contact=info.div (Example contact variable)

在这个"info"变量中，我得到了包含所有联系人详细信息的div，我想从这个div 中获取联系人号码

当我打印这个"info"变量时，它还显示变量中存在联系人编号，包括其他详细信息，但当我遍历div以获取联系人编号时，我找不到它。我还试图获得所有的子div，甚至包括div本身的类，我都无法获得

给出的第一个url是：https://www.yelp.com/search?find_desc=&find_loc=纽约+纽约%2C+纽约&ns=1

第二个url"url2"是这样的：https://www.yelp.com/biz/levain-bakery-new-york哪个有联系方式

有解决方案吗？？？

Answer 1

您可以在类名的帮助下获得联系电话。但我非常怀疑它是否适用于任何给定的页面，因为类名似乎是动态的。但你可以试一试。

from bs4 import BeautifulSoup as soup
from requests import get
url = "https://www.yelp.com/search?find_desc=&find_loc=New+York%2C+NY&ns=1"
clnt = get(url)
page=soup(clnt.text,"html.parser")
container = page.findAll("div",{"class":"lemon--div__373c0__1mboc container__373c0__ZB8u4 hoverable__373c0__3CcYQ margin-t3__373c0__1l90z margin-b3__373c0__q1DuY padding-t3__373c0__1gw9E padding-r3__373c0__57InZ padding-b3__373c0__342DA padding-l3__373c0__1scQ0 border--top__373c0__3gXLy border--right__373c0__1n3Iv border--bottom__373c0__3qNtD border--left__373c0__d1B7K border-color--default__373c0__3-ifU"})
container = container[1]
url2= "https://www.yelp.com"+container.a["href"]
clnt2 = get(url2)
page2 = soup(clnt2.text, 'html.parser')
info = page2.find("div",{"class":"lemon--div__373c0__1mboc island__373c0__3fs6U u-padding-t1 u-padding-r1 u-padding-b1 u-padding-l1 border--top__373c0__19Owr border--right__373c0__22AHO border--bottom__373c0__uPbXS border--left__373c0__1SjJs border-color--default__373c0__2oFDT background-color--white__373c0__GVEnp"})
ContactNumber = info.find("p",{"class":"lemon--p__373c0__3Qnnj text__373c0__2pB8f text-color--normal__373c0__K_MKN text-align--left__373c0__2pnx_"})
print(ContactNumber.text)

输出：

[phone]

Answer 2

以下对我有效：

from bs4 import BeautifulSoup as soup
from requests import get
url = "https://www.yelp.com/search?find_desc=&find_loc=New+York%2C+NY&ns=1"
clnt = get(url)
page=soup(clnt.text,"html.parser")
container = page.findAll("div",{"class":"lemon--div__373c0__1mboc container__373c0__ZB8u4 hoverable__373c0__3CcYQ margin-t3__373c0__1l90z margin-b3__373c0__q1DuY padding-t3__373c0__1gw9E padding-r3__373c0__57InZ padding-b3__373c0__342DA padding-l3__373c0__1scQ0 border--top__373c0__3gXLy border--right__373c0__1n3Iv border--bottom__373c0__3qNtD border--left__373c0__d1B7K border-color--default__373c0__3-ifU"})
container = container[1]
url2= "https://www.yelp.com"+container.a["href"]
clnt2 = get(url2)
page2 = soup(clnt2.text, 'html.parser')
info = page2.find("div",{"class":"lemon--div__373c0__1mboc island__373c0__3fs6U u-padding-t1 u-padding-r1 u-padding-b1 u-padding-l1 border--top__373c0__19Owr border--right__373c0__22AHO border--bottom__373c0__uPbXS border--left__373c0__1SjJs border-color--default__373c0__2oFDT background-color--white__373c0__GVEnp"})
p_tags_of_info = info.find_all("p")
print(p_tags_of_info[2].text)

我只是从info变量中提取了所有的<p>标签，然后选择了第三个<p>标签的文本。

Answer 3

试试这个。我尝试了第二个URL，它给出了一个联系电话。

url = 'https://www.yelp.com/biz/levain-bakery-new-york'
page = requests.get(url)
soup1 = BeautifulSoup(page.content, "lxml")
info = soup1.find_all("div", {
"class": "lemon--div__373c0__1mboc island-section__373c0__3vKXy border--top__373c0__19Owr border-color--default__373c0__2oFDT"})
contact_number = info[1].find("p", attrs={
'class': 'lemon--p__373c0__3Qnnj text__373c0__2pB8f text-color--normal__373c0__K_MKN text-align--left__373c0__2pnx_'}).text
print(contact_number)

如果答案有用，请予以批准。其他人可能会帮上忙。