Question

嗨，我正在尝试抓取医生及其地址的列表，但是我得到的是空列表我为该过程的必填字段，页面和类设置了定位器

这是我的代码：

import requests
from bs4 import BeautifulSoup
page_content=requests.get('https://easy.co.il/list/Orthopedics/?c2=5405').content
#assign locators
class QuoteLocators:
    DOCTOR_LOCATOR='p.biz-list-name'
    ADRESS_LOCATOR='p.biz-list-address'
class QuotesPageLocators:
    QUOTE = 'div.biz-item '
#assign pages
class QuotesPage:
    def __init__(self, page):
        self.soup = BeautifulSoup(page,'html.parser')

    @property
    def quotes(self):

        return [QuoteParser(e) for e in self.soup.select(QuotesPageLocators.QUOTE)]

#set parser
class QuoteParser:
    def __init__(self, parent):
        self.parent = parent

    def __repr__(self):
        return f'<Doctor  {self.name}, at {self.adress}>'

    @property
    def name(self):
        locator = QuoteLocators.DOCTOR_LOCATOR
        return self.parent.select_one(locator).string

    @property
    def adress(self):
        locator = QuoteLocators.ADRESS_LOCATOR
        return self.parent.select_one(locator).string

page=QuotesPage(page_content)

for quote in page.quotes:
    print(quote)

print(page.quotes)

Answer 1

您在页面上看到的数据是通过JavaScript从外部URL加载的。您可以使用此示例获取医生的姓名，地址：

// Validation before going to next page
wizard.on("beforeNext", function(wizardObj) {
  // validate the form and use below function to stop the wizard's step
  wizardObj.stop();
});

打印：

import re
import json
import requests
from bs4 import BeautifulSoup

url = 'https://easy.co.il/list/Orthopedics/?c2=5405'
c = re.search(r'var catid="(\d+)"', requests.get(url).text).group(1)
c2 = url.split('=')[-1]
api_url = 'https://easy.co.il/json/list.json?v=1.1&c={}&c2={}&listpage=1&lat=32.059925&lng=34.785126&rad=8905&mapid=0&viewport=desktop'.format(c, c2)

data = requests.get(api_url).json()

# uncomment this to print all data:
# print(json.dumps(data, indent=4))

for l in data['bizlist']['list']:
    print(l['bizname'])
    print(l['address'])
    print('-' * 80)

Web抓取python的Beautiful-soup

1 个答案: