通过登录主页来抓取主页的内部链接

import requests
from bs4 import BeautifulSoup

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}

url = 'https://example.com'
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')

for link in soup.find_all('a', href=True):
    if link['href'].startswith('https://example.com'):
        print(link['href'])

from selenium import webdriver

driver = webdriver.Chrome()
driver.get('https://example.com')

for link in driver.find_elements_by_tag_name('a'):
    if link.get_attribute('href').startswith('https://example.com'):
        print(link.get_attribute('href'))

driver.quit()

import requests
from bs4 import BeautifulSoup

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3'}

url = 'https://example.com'
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')

links = set()
for link in soup.find_all('a', href=True):
    if link['href'].startswith('https://example.com'):
        links.add(link['href'])

for link in links:
    print(link)