使用 python 获取 YouTube 播放列表网址

Question

如何获取播放列表 url 的存储方式

这里：https://www.youtube.com/watch?v=VpTRlS7EO6E&list=RDOIhVs0FQ8xc&index=5 用bs4？

使用

from bs4 import BeautifulSoup as bs
import requests

r = requests.get('https://www.youtube.com/watch?v=OIhVs0FQ8xc&list=RDOIhVs0FQ8xc&index=1')
page = r.text
soup=bs(page,'html.parser')
#print(soup)
res=soup.find_all('ytd-playlist-panel-video-renderer')
print(res)

不返回任何内容。即使打印汤本身也不包含我正在寻找的链接（如 href="/watch?v=puNOG62lf-Y&list=RDOIhVs0FQ8xc&index=2"）

Answer 1

这是一个 javascript 呈现的页面。你必须使用硒。

from bs4 import BeautifulSoup as bs
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
import time

url = 'https://www.youtube.com/watch?v=OIhVs0FQ8xc&list=RDOIhVs0FQ8xc&index=1'
driver = webdriver.Chrome(ChromeDriverManager().install())
driver.set_window_size(1024, 600)
driver.maximize_window()
driver.get(url)
time.sleep(2)

soup=bs(driver.page_source,'html.parser')
res=soup.find_all('ytd-playlist-panel-video-renderer')
print(res)

使用pip install webdriver-manager安装所需的包

Answer 2

谢谢！ 这里有一些对我有用的脏代码：

#--------------------------------- 
# import modules
from bs4 import BeautifulSoup as bs
from selenium import webdriver
import time
import re

#---------------------------------
#     
from webdriver_manager.firefox import GeckoDriverManager
driver = webdriver.Firefox(executable_path=GeckoDriverManager().install())

#---------------------------------
# get links from url    
def get_links(driver, sleep_time):

    # open driver window
    driver.set_window_size(1024, 600)
    driver.maximize_window()
    driver.get(url)    
            
    # wait some seconds
    time.sleep(sleep_time)
            
    # get information from url
    soup = bs(driver.page_source,'html.parser')
    res = soup.find_all('ytd-playlist-panel-video-renderer')  
            
    # check if there is information
    if len(res) > 0:
        main_url = 'https://www.youtube.com/watch?v='
        urls = re.findall('watch.*list', str(res))
        links = [main_url + str(a[8:-9]) for a in urls[::2]]
    # if there is no information return false
    else:
        links = False    
    return links

#---------------------------------
# set sleep timer
sleep_time = 10
# call function to get links
links = get_links(driver, sleep_time)

Answer 3

这对我有用：

from selenium import webdriver  # pip install selenium
import time

# make sure you download chrome driver from https://chromedriver.chromium.org/downloads and put it in folder 'driver'
driver = webdriver.Chrome('driver\chromedriver.exe')
driver.get('https://www.youtube.com/playlist?list=PLxvodScTx2RtAOoajGSu6ad4p8P8uXKQk')  # put here your link

# scroll page down
old_position = 0
new_position = None
position_script = """return (window.pageYOffset !== undefined) ?
          window.pageYOffset : (document.documentElement ||
          document.body.parentNode || document.body);"""
while new_position != old_position:
    old_position = driver.execute_script(position_script)
    time.sleep(1)
    driver.execute_script(
        """var scrollingElement = (document.scrollingElement ||
         document.body);scrollingElement.scrollTop =
         scrollingElement.scrollHeight;""")
    new_position = driver.execute_script(position_script)
source_page = driver.page_source
driver.quit()

# extract the url's and name's
counter = 1
element_to_find = 'amp;index={}" ar'
video_index = source_page.find(element_to_find.format(counter))  #'amp;index=1" ar'
while video_index != -1:
    title_element = ''
    count_name = video_index
    while title_element != 'title="':
        title_element = source_page[count_name: count_name + 7]
        count_name += 1
    count_name += 6
    start_title_position = count_name
    end_title = ''
    while end_title != '>':
        end_title = source_page[count_name]  # exit loop if end_title == '>'
        count_name += 1
    name = source_page[start_title_position:count_name - 2]  # extract the name of the video
    name = name.replace('"','"')
    video_id = source_page[video_index - 56: video_index - 45]  # extract video id
    print(str(counter)
          + '. link: ' + 'https://www.youtube.com/watch?v=' + video_id +
          ', name: ' + name)
    counter += 1
    video_index = source_page.find(element_to_find.format(counter))  # continue the next video