如何检查新的折扣，如果发现变化，如何发送到电报？

Question

我喜欢从网站上拿出新的折扣，并在网站上给我发电报和零钱。

这是可行的，但我得到了很多信息，我想改变脚本，以检查网站上的一个特定的class。

所以在网站上，我想检查一下<span class="space--ml-1 size--all-l size--fromW3-xl cept-discount">-49%</span>

如果值在-65%到-99%之间，我想要一条消息。这个是可能的吗？下面是检查更改的脚本：

import requests
from bs4 import BeautifulSoup
import difflib
import time
from datetime import datetime
import re
import os
import schedule
import cloudscraper


# target URL
url = "https://nl.pepper.com/groep/prijsfout"
# act like a browser
#headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36         (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
#headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36     (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246'}

scraper = cloudscraper.create_scraper()


# Send a message via a telegram bot
def telegram_bot_sendtext(bot_message):
bot_token = '17XXXX32:AAFd5jXXXXXXXXXXXXC5UJgG5pses8'
bot_chatID = '-XXXXX'
send_text = 'https://api.telegram.org/bot' + bot_token + '/sendMessage?chat_id=' + bot_chatID     + '&parse_mode=Markdown&text=' + bot_message

response = requests.get(send_text)

return response.json()


PrevVersion = ""
FirstRun = True
while True:

# download the page
response = scraper.get("https://nl.pepper.com/nieuw").content
# parse the downloaded homepage
soup =  BeautifulSoup(response, 'html.parser')

# remove all scripts and styles
for script in soup(["script", "style"]):
    script.extract()
soup = soup.get_text()
# compare the page text to the previous version
if PrevVersion != soup:
    # on the first run - just memorize the page
    if FirstRun == True:
        PrevVersion = soup
        FirstRun = False
        print ("Start Monitoring "+url+ ""+ str(datetime.now()))
    else:
        print ("Changes detected at: "+ str(datetime.now()))
        OldPage = PrevVersion.splitlines()
        NewPage = soup.splitlines()
        # compare versions and highlight changes using difflib
        #d = difflib.Differ()
        #diff = d.compare(OldPage, NewPage)
        diff = difflib.context_diff(OldPage,NewPage,n=0)
        out_text = "\n".join([ll.rstrip() for ll in '\n'.join(diff).splitlines() if     ll.strip()])
        print (out_text)
        OldPage = NewPage
        # Send the message (such as with a telegram bot provided below)
        telegram_bot_sendtext("Nieuwe prijsfout op Pepper " + url + out_text )

       # print ('\n'.join(diff))
        PrevVersion = soup
else:
    print( "No Changes "+ str(datetime.now()))
time.sleep(5)
continue

也许这个脚本中的cookie也有问题(或者它没有定义)。

Answer 1

如果有任何折扣在-65%到-99%之间，一个简单的可能的解决方案可能是：

此函数接受您的soup，并在一般情况下查找折扣，如果在您的范围内有任何折扣，则返回True；如果没有，则返回False：

def get_discounts(soup):
    for d in soup.select('.cept-discount'):
        if d.text != '' and 65 < int(''.join(filter(str.isdigit, d.text))) < 99:
            return True
        else:
            return False
        
get_discounts(soup)

Note在调用soup = soup.get_text()之前调用函数--顺序是将soup的内容更改为文本的关键原因。

最好将文本存储在另一个/重命名的变量中，例如souptext，.因此，您可以肯定，soup始终包含BeautifulSoup object__，它将document表示为嵌套的数据结构。

所以你最终会有这样的结果：

import requests, time, difflib, os, re, schedule, cloudscraper
from bs4 import BeautifulSoup
from datetime import datetime

# target URL
url = "https://nl.pepper.com/groep/prijsfout"
# act like a browser
#headers = {'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36         (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36'}
#headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36     (KHTML, like Gecko) Chrome/42.0.2311.135 Safari/537.36 Edge/12.246'}

scraper = cloudscraper.create_scraper()


# Send a message via a telegram bot
def telegram_bot_sendtext(bot_message):
    bot_token = '17XXXX32:AAFd5jXXXXXXXXXXXXC5UJgG5pses8'
    bot_chatID = '-XXXXX'
    send_text = 'https://api.telegram.org/bot' + bot_token + '/sendMessage?chat_id=' + bot_chatID     + '&parse_mode=Markdown&text=' + bot_message

    response = requests.get(send_text)

    return response.json()


PrevVersion = ""
FirstRun = True
while True:

    # download the page
    response = scraper.get("https://nl.pepper.com/nieuw").content
    # parse the downloaded homepage
    soup =  BeautifulSoup(response, 'html.parser')

    # remove all scripts and styles
    for script in soup(["script", "style"]):
        script.extract()
    discounts = get_discounts(soup)

    soup = soup.get_text()

    # compare the page text to the previous version and check if there are any discounts in your range

    if PrevVersion != soup and discounts:       
        # on the first run - just memorize the page
        if FirstRun == True:
            PrevVersion = soup
            FirstRun = False
            print ("Start Monitoring "+url+ ""+ str(datetime.now()))
        else:
            print ("Changes detected at: "+ str(datetime.now()))
            OldPage = PrevVersion.splitlines()
            NewPage = soup.splitlines()
            # compare versions and highlight changes using difflib
            #d = difflib.Differ()
            #diff = d.compare(OldPage, NewPage)
            diff = difflib.context_diff(OldPage,NewPage,n=0)
            out_text = "\n".join([ll.rstrip() for ll in '\n'.join(diff).splitlines() if     ll.strip()])
            print (out_text)
            OldPage = NewPage
            # Send the message (such as with a telegram bot provided below)
            telegram_bot_sendtext("Nieuwe prijsfout op Pepper " + url + out_text )

           # print ('\n'.join(diff))
            PrevVersion = soup
    else:
        print( "No Changes "+ str(datetime.now()))
    time.sleep(5)
    continue