find() 方法找不到我能找到的

Question

我一直在 python 开发网络抓取工具来抓取 Google 金融，但我无法使用 find() 方法找到我正在寻找的特定标签。最后气得我决定把返回的数据写到文件里自己找。所以我把它写到同一目录中的 testing.html，然后用 Google Chromium 打开它，这样我就可以使用检查工具了。几分钟之内，我就找到了我要找的元素。我究竟做错了什么？我的代码附在下面：

import dryscrape

session = dryscrape.Session()


def get(url):
    global session
    try:
        session.visit(url)
        data = session.body()
    except:
        print('Connection Failed')
    return str(data)

def save(price, stockname):
    pass

def extract(data):
    return data.find('<div class="YMLKec fxKbKc">')

class following():
    apple = "https://www.google.com/finance/quote/AAPL:NASDAQ"
    tesla = "https://www.google.com/finance/quote/TSLA:NASDAQ"
    google = "https://www.google.com/finance/quote/GOOGL:NASDAQ"
    amazon = "https://www.google.com/finance/quote/AMZN:NASDAQ"
    microsoft = "https://www.google.com/finance/quote/MSFT:NASDAQ"
    netflix = "https://www.google.com/finance/quote/NFLX:NASDAQ"
    def __init__():
        global apple
        global tesla
        global google
        global amazon
        global microsoft
        global netflix
        save(extract(get(following.apple)), following.apple)
        save(extract(get(following.tesla)), following.tesla)
        save(extract(get(following.google)), following.google)
        save(extract(get(following.amazon)), following.amazon)
        save(extract(get(following.microsoft)), following.microsoft)
        save(extract(get(following.netflix)), following.netflix)

f = open("testing.html")
print(extract(f.read()))
f.close()

Answer 1

为什么不尝试使用请求和 BeautifulSoup 库呢？以下是我的意思。

import requests
from bs4 import BeautifulSoup


class following():

    def __init__(self):
        self.session = requests.Session()
        self.session.headers['User-Agent'] = 'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.104 Safari/537.36'

    def get_last_price(self,link):
        r = self.session.get(link)
        return BeautifulSoup(r.text,"lxml")

    def extract(self,soup):
        return soup.select_one("[data-exchange='NASDAQ']")['data-last-price']


if __name__ == '__main__':
    base = "https://www.google.com/finance/quote/{}:NASDAQ"
    scraper = following()

    for ticker in ['AAPL','TSLA','GOOGL','AMZN','MSFT','NFLX']:
        soup_object = scraper.get_last_price(base.format(ticker))
        print(scraper.extract(soup_object))

Answer 2

发现问题：不是 YMLKec，而是 YMlKec。不是大写 L.

data = open("testing.html", "r").read()
class_ = "YMlKec fxKbKc"
print(data.find(class_))
>>> 992880

find() 方法找不到我能找到的

find() Method Can't Find What I Can

python

web-scraping

dryscrape