抖音網頁版高清視頻抓取教程selenium

廢話不多說，直接上代碼

from selenium import webdriver
from selenium.webdriver import ChromeOptions
import time
import re
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
import uuid
import os
import requests

option = ChromeOptions()
option.add_argument(
    'user-agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36"'
)
option.add_experimental_option('excludeSwitches', ['enable-automation'])  # 防止系統檢測到自動化工具
option.add_experimental_option('useAutomationExtension', False)
browser = webdriver.Chrome(options=option)
browser.execute_cdp_cmd('Page.addScriptToEvaluateOnNewDocument', {
    'source': 'Object.defineProperty(navigator, "webdriver", {get: () => undefined})'
})

browser.maximize_window()  # 頁面最大化


def douyincrawler(keyword):
    url = 'https://www.douyin.com/search/' + keyword + '?publish_time=0&sort_type=0&source=switch_tab&type=video'
    browser.get(url)
    browser.find_element_by_xpath('//*[@id="qdblhsHs"]/button').click()  # 點擊登陸用抖音手機app掃碼登陸
    time.sleep(15)  # 設置等待時間掃碼登陸

    for x in range(10):  # 自動下拉
        time.sleep(5)
        js_bottom = "var q=document.documentElement.scrollTop=10000"
        browser.execute_script(js_bottom)
        if '服務出現異常' in browser.page_source:  # 刷新頁面
            browser.refresh()
        if '服務異常，重新' in browser.page_source:
            browser.find_element_by_xpath('//*[@id="dark"]/div[2]/div/div[3]/div[2]/div/div/span').click()  # 點擊加載

    video_id_lists = list(set(re.findall(r'<a href="//www.douyin.com/video/(.*?)"',browser.page_source)))
    detail_url_lists = ['https://www.douyin.com/video/' + i for i in video_id_lists]
    print('共計獲取到{}個視頻'.format(len(detail_url_lists)))
    for i in detail_url_lists:
        js = "window.open('{}')".format(i)  #打開新tab頁
        browser.execute_script(js)
        ws = browser.window_handles  # 獲取所有窗口
        browser.switch_to.window(ws[1])  # 切換新句柄
        WebDriverWait(browser, 10).until(EC.presence_of_element_located((
            By.XPATH, "//xg-video-container[@class='xg-video-container']/video"
        )))  # 顯示等待視頻標簽出現
        video_url = 'https:' + re.findall(r'<source class="" src="(.*?)"', browser.page_source)[0]  # 正則獲取視頻鏈接
        savevideo(video_url)
        browser.close()  # 關閉當前窗口
        browser.switch_to.window(ws[0])  # 切回主頁面這一步很關鍵



def savevideo(video_url):
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.90 Safari/537.36",
    }
    video_dir = r'F:\2022_09_01\yan_ming\jian_kong_video\douyin_video'
    video_full_path = os.path.join(video_dir, str(uuid.uuid4()) + '.mp4')
    response = requests.get(url=video_url, headers=headers)
    with open(video_full_path, 'wb') as f:
        f.write(response.content)
    print('已下載：{}'.format(video_url))


if __name__ == '__main__':
    douyincrawler('街拍美女')

成果展示：

 

注：該代碼只做技術分享，不可用於違法犯罪