如果檢測到更改，如何檢查新折扣并發送到電報？-有解無憂

我喜歡從網站上獲取新的折扣，并通過電報給我發短信，并在網站上進行更改。

這是有效的，但我收到了很多訊息，我想更改腳本以檢查class網站上的特定內容。

所以在網站上我想檢查 <span >-49%</span>

如果值介于 -65% 和 -99% 之間，我想要一條訊息。這可能嗎？檢查更改的腳本如下：

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

也許這個腳本中的cookies也有問題（或者沒有定義。）

uj5u.com熱心網友回復：

如果在 -65% 和 -99% 之間有任何折扣，一個簡單的可能解決方案可能如下所示。

此功能正在獲取您的soup并正在尋找一般的折扣，True如果您的范圍內有任何折扣或False沒有折扣，則回傳：

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)

注意 在呼叫之前呼叫函式soup = soup.get_text()- 順序是至關重要的，因為您將的內容更改soup為文本。

將文本存盤在另一個/重命名的變數中可能會更好，例如souptext，......所以你可以肯定，它soup總是包含BeautifulSoup object，它表示document作為嵌套資料結構。

所以你最終會得到這樣的結果：

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

轉載請註明出處，本文鏈接：https://www.uj5u.com/qianduan/381336.html

標籤：Python 网络刮

上一篇：PHP使用header("Location:")重定向到不同的url不起作用

下一篇：WSGI框架的替代方案