mirror of
https://github.com/Evil0ctal/Douyin_TikTok_Download_API.git
synced 2025-04-23 00:29:23 +08:00
🐛 Fix the TikTok pictures album
This commit is contained in:
parent
7961f11e1e
commit
86683c8219
154
scraper.py
154
scraper.py
@ -2,7 +2,7 @@
|
|||||||
# -*- encoding: utf-8 -*-
|
# -*- encoding: utf-8 -*-
|
||||||
# @Author: https://github.com/Evil0ctal/
|
# @Author: https://github.com/Evil0ctal/
|
||||||
# @Time: 2021/11/06
|
# @Time: 2021/11/06
|
||||||
# @Update: 2022/07/29
|
# @Update: 2022/08/08
|
||||||
# @Function:
|
# @Function:
|
||||||
# 核心代码,估值1块(๑•̀ㅂ•́)و✧
|
# 核心代码,估值1块(๑•̀ㅂ•́)و✧
|
||||||
# 用于爬取Douyin/TikTok数据并以字典形式返回。
|
# 用于爬取Douyin/TikTok数据并以字典形式返回。
|
||||||
@ -334,16 +334,81 @@ class Scraper:
|
|||||||
except:
|
except:
|
||||||
video_info = None
|
video_info = None
|
||||||
# 从TikTok官方API获取部分视频数据
|
# 从TikTok官方API获取部分视频数据
|
||||||
# 新API2022年7月29日 https://api.tiktokv.com/aweme/v1/aweme/detail/?aweme_id={}
|
|
||||||
# 旧API https://api.tiktokv.com/aweme/v1/multi/aweme/detail/?aweme_ids=%5B{}%5D
|
|
||||||
tiktok_api_link = 'https://api.tiktokv.com/aweme/v1/aweme/detail/?aweme_id={}'.format(
|
tiktok_api_link = 'https://api.tiktokv.com/aweme/v1/aweme/detail/?aweme_id={}'.format(
|
||||||
video_id)
|
video_id)
|
||||||
print('正在请求API链接:{}'.format(tiktok_api_link))
|
print('正在请求API链接:{}'.format(tiktok_api_link))
|
||||||
response = requests.get(url=tiktok_api_link, headers=headers, proxies=self.proxies).text
|
response = requests.get(url=tiktok_api_link, headers=headers, proxies=self.proxies).text
|
||||||
# 将API获取到的内容格式化为JSON
|
# 将API获取到的内容格式化为JSON
|
||||||
result = json.loads(response)
|
result = json.loads(response)
|
||||||
for i in result["aweme_detail"]:
|
if 'image_post_info' in response:
|
||||||
if i != 'image_post_info':
|
# 判断链接是图集链接
|
||||||
|
url_type = 'album'
|
||||||
|
print('类型为图集')
|
||||||
|
# 视频标题
|
||||||
|
album_title = result["aweme_detail"]["desc"]
|
||||||
|
# 视频作者昵称
|
||||||
|
album_author_nickname = result["aweme_detail"]['author']["nickname"]
|
||||||
|
# 视频作者ID
|
||||||
|
album_author_id = result["aweme_detail"]['author']["unique_id"]
|
||||||
|
# 上传时间戳
|
||||||
|
album_create_time = result["aweme_detail"]['create_time']
|
||||||
|
# 视频ID
|
||||||
|
album_aweme_id = result["aweme_detail"]['statistics']['aweme_id']
|
||||||
|
try:
|
||||||
|
# 视频BGM标题
|
||||||
|
album_music_title = result["aweme_detail"]['music']['title']
|
||||||
|
# 视频BGM作者
|
||||||
|
album_music_author = result["aweme_detail"]['music']['author']
|
||||||
|
# 视频BGM ID
|
||||||
|
album_music_id = result["aweme_detail"]['music']['id']
|
||||||
|
# 视频BGM链接
|
||||||
|
album_music_url = result["aweme_detail"]['music']['play_url']['url_list'][0]
|
||||||
|
except:
|
||||||
|
album_music_title, album_music_author, album_music_id, album_music_url = "None", "None", "None", "None"
|
||||||
|
# 评论数量
|
||||||
|
album_comment_count = result["aweme_detail"]['statistics']['comment_count']
|
||||||
|
# 获赞数量
|
||||||
|
album_digg_count = result["aweme_detail"]['statistics']['digg_count']
|
||||||
|
# 播放次数
|
||||||
|
album_play_count = result["aweme_detail"]['statistics']['play_count']
|
||||||
|
# 下载次数
|
||||||
|
album_download_count = result["aweme_detail"]['statistics']['download_count']
|
||||||
|
# 分享次数
|
||||||
|
album_share_count = result["aweme_detail"]['statistics']['share_count']
|
||||||
|
# 无水印图集
|
||||||
|
album_list = []
|
||||||
|
for i in result["aweme_detail"]['image_post_info']['images']:
|
||||||
|
album_list.append(i['display_image']['url_list'][0])
|
||||||
|
# 结束时间
|
||||||
|
end = time.time()
|
||||||
|
# 解析时间
|
||||||
|
analyze_time = format((end - start), '.4f')
|
||||||
|
# 储存数据
|
||||||
|
album_data = {'status': 'success',
|
||||||
|
'analyze_time': (analyze_time + 's'),
|
||||||
|
'url_type': url_type,
|
||||||
|
'api_url': tiktok_api_link,
|
||||||
|
'original_url': original_url,
|
||||||
|
'platform': 'tiktok',
|
||||||
|
'album_title': album_title,
|
||||||
|
'album_list': album_list,
|
||||||
|
'album_author_nickname': album_author_nickname,
|
||||||
|
'album_author_id': album_author_id,
|
||||||
|
'album_create_time': album_create_time,
|
||||||
|
'album_aweme_id': album_aweme_id,
|
||||||
|
'album_music_title': album_music_title,
|
||||||
|
'album_music_author': album_music_author,
|
||||||
|
'album_music_id': album_music_id,
|
||||||
|
'album_music_url': album_music_url,
|
||||||
|
'album_comment_count': album_comment_count,
|
||||||
|
'album_digg_count': album_digg_count,
|
||||||
|
'album_play_count': album_play_count,
|
||||||
|
'album_share_count': album_share_count,
|
||||||
|
'album_download_count': album_download_count
|
||||||
|
}
|
||||||
|
# 返回包含数据的字典
|
||||||
|
return album_data
|
||||||
|
else:
|
||||||
# 类型为视频
|
# 类型为视频
|
||||||
url_type = 'video'
|
url_type = 'video'
|
||||||
print('类型为视频')
|
print('类型为视频')
|
||||||
@ -460,85 +525,6 @@ class Scraper:
|
|||||||
}
|
}
|
||||||
# 返回包含数据的字典
|
# 返回包含数据的字典
|
||||||
return video_data
|
return video_data
|
||||||
else:
|
|
||||||
# 判断链接是图集链接
|
|
||||||
# https://www.tiktok.com/@tamm6636/video/7105440975878655278
|
|
||||||
video_id = re.findall('video/(\d+)?', original_url)[0]
|
|
||||||
print('视频ID为: {}'.format(video_id))
|
|
||||||
# 从TikTok官方API获取部分视频数据
|
|
||||||
tiktok_api_link = 'https://api.tiktokv.com/aweme/v1/multi/aweme/detail/?aweme_ids=%5B{}%5D'.format(
|
|
||||||
video_id)
|
|
||||||
print('正在请求API链接:{}'.format(tiktok_api_link))
|
|
||||||
response = requests.get(url=tiktok_api_link, headers=headers, proxies=self.proxies).text
|
|
||||||
# 将API获取到的内容格式化为JSON
|
|
||||||
result = json.loads(response)
|
|
||||||
# 类型为图集
|
|
||||||
url_type = 'album'
|
|
||||||
print('类型为图集')
|
|
||||||
# 视频标题
|
|
||||||
album_title = result["aweme_detail"]["desc"]
|
|
||||||
# 视频作者昵称
|
|
||||||
album_author_nickname = result["aweme_detail"]['author']["nickname"]
|
|
||||||
# 视频作者ID
|
|
||||||
album_author_id = result["aweme_detail"]['author']["unique_id"]
|
|
||||||
# 上传时间戳
|
|
||||||
album_create_time = result["aweme_detail"]['create_time']
|
|
||||||
# 视频ID
|
|
||||||
album_aweme_id = result["aweme_detail"]['statistics']['aweme_id']
|
|
||||||
try:
|
|
||||||
# 视频BGM标题
|
|
||||||
album_music_title = result["aweme_detail"]['music']['title']
|
|
||||||
# 视频BGM作者
|
|
||||||
album_music_author = result["aweme_detail"]['music']['author']
|
|
||||||
# 视频BGM ID
|
|
||||||
album_music_id = result["aweme_detail"]['music']['id']
|
|
||||||
# 视频BGM链接
|
|
||||||
album_music_url = result["aweme_detail"]['music']['play_url']['url_list'][0]
|
|
||||||
except:
|
|
||||||
album_music_title, album_music_author, album_music_id, album_music_url = "None", "None", "None", "None"
|
|
||||||
# 评论数量
|
|
||||||
album_comment_count = result["aweme_detail"]['statistics']['comment_count']
|
|
||||||
# 获赞数量
|
|
||||||
album_digg_count = result["aweme_detail"]['statistics']['digg_count']
|
|
||||||
# 播放次数
|
|
||||||
album_play_count = result["aweme_detail"]['statistics']['play_count']
|
|
||||||
# 下载次数
|
|
||||||
album_download_count = result["aweme_detail"]['statistics']['download_count']
|
|
||||||
# 分享次数
|
|
||||||
album_share_count = result["aweme_detail"]['statistics']['share_count']
|
|
||||||
# 无水印图集
|
|
||||||
album_list = []
|
|
||||||
for i in result["aweme_detail"]['image_post_info']['images']:
|
|
||||||
album_list.append(i['display_image']['url_list'][0])
|
|
||||||
# 结束时间
|
|
||||||
end = time.time()
|
|
||||||
# 解析时间
|
|
||||||
analyze_time = format((end - start), '.4f')
|
|
||||||
# 储存数据
|
|
||||||
album_data = {'status': 'success',
|
|
||||||
'analyze_time': (analyze_time + 's'),
|
|
||||||
'url_type': url_type,
|
|
||||||
'api_url': tiktok_api_link,
|
|
||||||
'original_url': original_url,
|
|
||||||
'platform': 'tiktok',
|
|
||||||
'album_title': album_title,
|
|
||||||
'album_list': album_list,
|
|
||||||
'album_author_nickname': album_author_nickname,
|
|
||||||
'album_author_id': album_author_id,
|
|
||||||
'album_create_time': album_create_time,
|
|
||||||
'album_aweme_id': album_aweme_id,
|
|
||||||
'album_music_title': album_music_title,
|
|
||||||
'album_music_author': album_music_author,
|
|
||||||
'album_music_id': album_music_id,
|
|
||||||
'album_music_url': album_music_url,
|
|
||||||
'album_comment_count': album_comment_count,
|
|
||||||
'album_digg_count': album_digg_count,
|
|
||||||
'album_play_count': album_play_count,
|
|
||||||
'album_share_count': album_share_count,
|
|
||||||
'album_download_count': album_download_count
|
|
||||||
}
|
|
||||||
# 返回包含数据的字典
|
|
||||||
return album_data
|
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
# 异常捕获
|
# 异常捕获
|
||||||
return {'status': 'failed', 'reason': e, 'function': 'Scraper.tiktok()', 'value': original_url}
|
return {'status': 'failed', 'reason': e, 'function': 'Scraper.tiktok()', 'value': original_url}
|
||||||
|
Loading…
x
Reference in New Issue
Block a user