實戰(zhàn)：帶你用Python爬取抖音app視頻

http://v1-dy.ixigua.com/；http://v3-dy.ixigua.com/；http://v9-dy.ixigua.com/

import requests# 文件路徑path = 'D:/video/'num = 1788

def response(flow):    global num    # 經(jīng)測試發(fā)現(xiàn)視頻url前綴主要是3個    target_urls = ['http://v1-dy.ixigua.com/', 'http://v9-dy.ixigua.com/',                   'http://v3-dy.ixigua.com/']    for url in target_urls:        # 過濾掉不需要的url        if flow.request.url.startswith(url):            # 設置視頻名            filename = path + str(num) + '.mp4'            # 使用request獲取視頻url的內(nèi)容            # stream=True作用是推遲下載響應體直到訪問Response.content屬性            res = requests.get(flow.request.url, stream=True)            # 將視頻寫入文件夾            with open(filename, 'ab') as f:                f.write(res.content)                f.flush()                print(filename + '下載完成')            num += 1

{  "platformName": "Android",  "deviceName": "Mi_Note_3",  "appPackage": "com.ss.android.ugc.aweme",  "appActivity": ".main.MainActivity"}

from appium import webdriverfrom time import sleep

class Action():    def __init__(self):        # 初始化配置，設置Desired Capabilities參數(shù)        self.desired_caps = {            "platformName": "Android",            "deviceName": "Mi_Note_3",            "appPackage": "com.ss.android.ugc.aweme",            "appActivity": ".main.MainActivity"        }        # 指定Appium Server        self.server = 'http://localhost:4723/wd/hub'        # 新建一個Session        self.driver = webdriver.Remote(self.server, self.desired_caps)        # 設置滑動初始坐標和滑動距離        self.start_x = 500        self.start_y = 1500        self.distance = 1300
    def comments(self):        sleep(2)        # app開啟之后點擊一次屏幕，確保頁面的展示        self.driver.tap([(500, 1200)], 500)
    def scroll(self):        # 無限滑動        while True:            # 模擬滑動            self.driver.swipe(self.start_x, self.start_y, self.start_x,                               self.start_y-self.distance)            # 設置延時等待            sleep(2)
    def main(self):        self.comments()        self.scroll()

if __name__ == '__main__':
    action = Action()    action.main()