|
| 1 | +# -*- coding:utf-8 -*- |
| 2 | +from splinter.driver.webdriver.chrome import Options, Chrome |
| 3 | +from splinter.browser import Browser |
| 4 | +from contextlib import closing |
| 5 | +import requests, json, time, re, os, sys, time |
| 6 | +from bs4 import BeautifulSoup |
| 7 | + |
| 8 | +class DouYin(object): |
| 9 | + def __init__(self, width = 500, height = 300): |
| 10 | + """ |
| 11 | + 抖音App视频下载 |
| 12 | + """ |
| 13 | + # 无头浏览器 |
| 14 | + chrome_options = Options() |
| 15 | + chrome_options.add_argument('user-agent="Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"') |
| 16 | + self.driver = Browser(driver_name='chrome', executable_path='D:/chromedriver', options=chrome_options, headless=True) |
| 17 | + |
| 18 | + def get_video_urls(self, user_id): |
| 19 | + """ |
| 20 | + 获得视频播放地址 |
| 21 | + Parameters: |
| 22 | + user_id：查询的用户ID |
| 23 | + Returns: |
| 24 | + video_names: 视频名字列表 |
| 25 | + video_urls: 视频链接列表 |
| 26 | + nickname: 用户昵称 |
| 27 | + """ |
| 28 | + video_names = [] |
| 29 | + video_urls = [] |
| 30 | + unique_id = '' |
| 31 | + while unique_id != user_id: |
| 32 | + search_url = 'https://api.amemv.com/aweme/v1/discover/search/?cursor=0&keyword=%s&count=10&type=1&retry_type=no_retry&iid=17900846586&device_id=34692364855&ac=wifi&channel=xiaomi&aid=1128&app_name=aweme&version_code=162&version_name=1.6.2&device_platform=android&ssmix=a&device_type=MI+5&device_brand=Xiaomi&os_api=24&os_version=7.0&uuid=861945034132187&openudid=dc451556fc0eeadb&manifest_version_code=162&resolution=1080*1920&dpi=480&update_version_code=1622' % user_id |
| 33 | + req = requests.get(url = search_url, verify = False) |
| 34 | + html = json.loads(req.text) |
| 35 | + aweme_count = html['user_list'][0]['user_info']['aweme_count'] |
| 36 | + uid = html['user_list'][0]['user_info']['uid'] |
| 37 | + nickname = html['user_list'][0]['user_info']['nickname'] |
| 38 | + unique_id = html['user_list'][0]['user_info']['unique_id'] |
| 39 | + user_url = 'https://www.douyin.com/aweme/v1/aweme/post/?user_id=%s&max_cursor=0&count=%s' % (uid, aweme_count) |
| 40 | + req = requests.get(url = user_url, verify = False) |
| 41 | + html = json.loads(req.text) |
| 42 | + i = 1 |
| 43 | + for each in html['aweme_list']: |
| 44 | + share_desc = each['share_info']['share_desc'] |
| 45 | + if '抖音-原创音乐短视频社区' == share_desc: |
| 46 | + video_names.append(str(i) + '.mp4') |
| 47 | + i += 1 |
| 48 | + else: |
| 49 | + video_names.append(share_desc + '.mp4') |
| 50 | + video_urls.append(each['share_info']['share_url']) |
| 51 | + |
| 52 | + return video_names, video_urls, nickname |
| 53 | + |
| 54 | + def get_download_url(self, video_url): |
| 55 | + """ |
| 56 | + 获得带水印的视频播放地址 |
| 57 | + Parameters: |
| 58 | + video_url：带水印的视频播放地址 |
| 59 | + Returns: |
| 60 | + download_url: 带水印的视频下载地址 |
| 61 | + """ |
| 62 | + req = requests.get(url = video_url, verify = False) |
| 63 | + bf = BeautifulSoup(req.text, 'lxml') |
| 64 | + script = bf.find_all('script')[-1] |
| 65 | + video_url_js = re.findall('var data = \[(.+)\];', str(script))[0] |
| 66 | + video_html = json.loads(video_url_js) |
| 67 | + download_url = video_html['video']['play_addr']['url_list'][0] |
| 68 | + return download_url |
| 69 | + |
| 70 | + def video_downloader(self, video_url, video_name, watermark_flag=True): |
| 71 | + """ |
| 72 | + 视频下载 |
| 73 | + Parameters: |
| 74 | + video_url: 带水印的视频地址 |
| 75 | + video_name: 视频名 |
| 76 | + watermark_flag: 是否下载不带水印的视频 |
| 77 | + Returns: |
| 78 | + 无 |
| 79 | + """ |
| 80 | + size = 0 |
| 81 | + if watermark_flag == True: |
| 82 | + video_url = self.remove_watermark(video_url) |
| 83 | + else: |
| 84 | + video_url = self.get_download_url(video_url) |
| 85 | + with closing(requests.get(video_url, stream=True, verify = False)) as response: |
| 86 | + chunk_size = 1024 |
| 87 | + content_size = int(response.headers['content-length']) |
| 88 | + if response.status_code == 200: |
| 89 | + sys.stdout.write(' [文件大小]:%0.2f MB\n' % (content_size / chunk_size / 1024)) |
| 90 | + |
| 91 | + with open(video_name, "wb") as file: |
| 92 | + for data in response.iter_content(chunk_size = chunk_size): |
| 93 | + file.write(data) |
| 94 | + size += len(data) |
| 95 | + file.flush() |
| 96 | + |
| 97 | + sys.stdout.write(' [下载进度]:%.2f%%' % float(size / content_size * 100) + '\r') |
| 98 | + sys.stdout.flush() |
| 99 | + |
| 100 | + |
| 101 | + def remove_watermark(self, video_url): |
| 102 | + """ |
| 103 | + 获得无水印的视频播放地址 |
| 104 | + Parameters: |
| 105 | + video_url: 带水印的视频地址 |
| 106 | + Returns: |
| 107 | + 无水印的视频下载地址 |
| 108 | + """ |
| 109 | + self.driver.visit('http://douyin.iiilab.com/') |
| 110 | + self.driver.find_by_tag('input').fill(video_url) |
| 111 | + self.driver.find_by_xpath('//button[@class="btn btn-default"]').click() |
| 112 | + html = self.driver.find_by_xpath('//div[@class="thumbnail"]/div/p')[0].html |
| 113 | + bf = BeautifulSoup(html, 'lxml') |
| 114 | + return bf.find('a').get('href') |
| 115 | + |
| 116 | + def run(self): |
| 117 | + """ |
| 118 | + 运行函数 |
| 119 | + Parameters: |
| 120 | + None |
| 121 | + Returns: |
| 122 | + None |
| 123 | + """ |
| 124 | + self.hello() |
| 125 | + user_id = input('请输入ID(例如40103580):') |
| 126 | + video_names, video_urls, nickname = self.get_video_urls(user_id) |
| 127 | + if nickname not in os.listdir(): |
| 128 | + os.mkdir(nickname) |
| 129 | + print('视频下载中:共有%d个作品!\n' % len(video_urls)) |
| 130 | + for num in range(len(video_urls)): |
| 131 | + print(' 解析第%d个视频链接 [%s] 中，请稍后!\n' % (num+1, video_urls[num])) |
| 132 | + if '\\' in video_names[num]: |
| 133 | + video_name = video_names[num].replace('\\', '') |
| 134 | + elif '/' in video_names[num]: |
| 135 | + video_name = video_names[num].replace('/', '') |
| 136 | + else: |
| 137 | + video_name = video_names[num] |
| 138 | + self.video_downloader(video_urls[num], os.path.join(nickname, video_name)) |
| 139 | + print('\n') |
| 140 | + |
| 141 | + print('下载完成!') |
| 142 | + |
| 143 | + def hello(self): |
| 144 | + """ |
| 145 | + 打印欢迎界面 |
| 146 | + Parameters: |
| 147 | + None |
| 148 | + Returns: |
| 149 | + None |
| 150 | + """ |
| 151 | + print('*' * 100) |
| 152 | + print('\t\t\t\t抖音App视频下载小助手') |
| 153 | + print('\t\t作者:Jack Cui') |
| 154 | + print('*' * 100) |
| 155 | + |
| 156 | + |
| 157 | +if __name__ == '__main__': |
| 158 | + douyin = DouYin() |
| 159 | + douyin.run() |
0 commit comments