抓取url不变的网站[python with beautiful soup]

我是一个全新的网页抓取。 我怎样才能抓取一个url不随页码变化的网站？ 假设以这个网站为例- url不随页码变化， 这和我要问的一样，我们如何使用python中的beautiful soup来实现它呢

import requests
from bs4 import BeautifulSoup


url = 'https://www.bseindia.com/corporates/Forth_Results.aspx'
headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0'}

soup = BeautifulSoup(requests.get(url, headers=headers).content, 'html.parser')

page = 1
while True:
    print(page)
    rows = soup.select('.TTRow')
    if not rows:
        break

    # print some data to screen:
    for tr in rows:
        print(tr.get_text(strip=True, separator=' '))

    # to get correct page, you have to do POST request with correct data
    # the data is located in <input name="..." value=".."> tags
    d = {}
    for i in soup.select('input'):
        d[i['name']] = i.get('value', '')

    # some data parameters needs to be deleted:
    if 'ctl00$ContentPlaceHolder1$btnSubmit' in d:
        del d['ctl00$ContentPlaceHolder1$btnSubmit']

    # set correct page:
    page += 1
    d['__EVENTTARGET'] = 'ctl00$ContentPlaceHolder1$gvData'
    d['__EVENTARGUMENT'] = 'Page${}'.format(page)

    soup = BeautifulSoup(requests.post(url, headers=headers, data=d).content, 'html.parser')

编辑：要将其保存为CSV，可以使用以下命令：

import requests
import pandas as pd
from bs4 import BeautifulSoup


url = 'https://www.bseindia.com/corporates/Forth_Results.aspx'
headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0'}

soup = BeautifulSoup(requests.get(url, headers=headers).content, 'html.parser')

page = 1
all_data = []
while True:
    print(page)
    rows = soup.select('.TTRow')
    if not rows:
        break

    # print some data to screen:
    for tr in rows:
        row = tr.get_text(strip=True, separator='|').split('|')
        all_data.append(row)

    # to get correct page, you have to do POST request with correct data
    # the data is located in <input name="..." value=".."> tags
    d = {}
    for i in soup.select('input'):
        d[i['name']] = i.get('value', '')

    # some data parameters needs to be deleted:
    if 'ctl00$ContentPlaceHolder1$btnSubmit' in d:
        del d['ctl00$ContentPlaceHolder1$btnSubmit']

    # set correct page:
    page += 1
    d['__EVENTTARGET'] = 'ctl00$ContentPlaceHolder1$gvData'
    d['__EVENTARGUMENT'] = 'Page${}'.format(page)

    soup = BeautifulSoup(requests.post(url, headers=headers, data=d).content, 'html.parser')

df = pd.DataFrame(all_data)
print(df)
df.to_csv('data.csv')

从LibreOffice生成data.csv屏幕截图：

---

此网站由javascript控制。我认为BeautifulSoup无法处理此类网站。人们经常使用Selenium来刮它们。我想你可以找到你的答案：谢谢你，先生，我能把它保存在excel或csv文件中吗？？“有三个不同的id、名称和日期栏，请您也添加注释，这样我就可以相应地修改代码了。”Prabhatkumar更新了我的答案。

import requests
import pandas as pd
from bs4 import BeautifulSoup


url = 'https://www.bseindia.com/corporates/Forth_Results.aspx'
headers = {'User-Agent': 'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:78.0) Gecko/20100101 Firefox/78.0'}

soup = BeautifulSoup(requests.get(url, headers=headers).content, 'html.parser')

page = 1
all_data = []
while True:
    print(page)
    rows = soup.select('.TTRow')
    if not rows:
        break

    # print some data to screen:
    for tr in rows:
        row = tr.get_text(strip=True, separator='|').split('|')
        all_data.append(row)

    # to get correct page, you have to do POST request with correct data
    # the data is located in <input name="..." value=".."> tags
    d = {}
    for i in soup.select('input'):
        d[i['name']] = i.get('value', '')

    # some data parameters needs to be deleted:
    if 'ctl00$ContentPlaceHolder1$btnSubmit' in d:
        del d['ctl00$ContentPlaceHolder1$btnSubmit']

    # set correct page:
    page += 1
    d['__EVENTTARGET'] = 'ctl00$ContentPlaceHolder1$gvData'
    d['__EVENTARGUMENT'] = 'Page${}'.format(page)

    soup = BeautifulSoup(requests.post(url, headers=headers, data=d).content, 'html.parser')

df = pd.DataFrame(all_data)
print(df)
df.to_csv('data.csv')