https://gitee.com/erma0/douyin
Python取数据 + Vue写界面 + Aria2下载
根据抖音各种链接或各种id，通过网页接口采集视频作品，并下载作品到本地。
支持用户主页链接或sec_uid/话题挑战和音乐原声链接或ID。
支持下载喜欢列表（需喜欢列表可见）。
在程序目录打开命令行，输入
pip install -r requirements.txt双击打开启动.bat，或者在程序目录打开命令行，输入
python ui.pydouyin.py中相关参数使用完全不懂Python的朋友用命令行或操作界面。
exec.py-h参数查看帮助python exec.py
python exec.py -h
python exec.py download -h
python exec.py download_batch -h--type 指定下载类型，默认值：--type=user
--limit 指定采集数量，默认值：--limit=0（不限制）例如采集某用户全部作品：
python exec.py download https://v.douyin.com/xxxx/
python exec.py download 用户的secuid例如采集某用户喜欢的前10个作品：
python exec.py download MS4wLjABAAAAl7TJWjJJrnu11IlllB6Mi5V9VbAsQo1N987guPjctc8 --type=like --limit=10
python exec.py download 用户的secuid例如采集某音乐原声前10个作品：
python exec.py download https://v.douyin.com/xxxx/ --type=music --limit=10
python exec.py download 音乐ID --type=music --limit=10Aria2c.exe来开启服务，所以要用代码实现自动启动服务--auto-file-renaming=false 可行，但控制台使用会报错，虽然报错不影响-c 可行，且控制台不报错options = {'out': filename}指定文件名，即-dDownload.title2path静态方法os.popen或subprocess.Popen实现子进程打开程序，无界面，不阻塞if 'PROGRAMFILES(X86)' in os.environ简单判断系统是否为64位launch.json中加一句"cwd": "${fileDirname}",即可，不过自动补全pylance就无法识别相对目录了pipreqs ./ --encoding=utf-8 --forcepywebview.api.func().then(() => {})调用Python函数window.evaluate_js('JS代码')调用JS方法_开头# -*- encoding: utf-8 -*-
'''
@File : douyin.py
home.php?mod=space&uid=116177 : 2021年03月12日 18:16:57 星期五
@Author : erma0
home.php?mod=space&uid=59980 : 1.0
home.php?mod=space&uid=95579 : https://erma0.cn
@Desc : 抖音用户作品采集
'''
import json
import os
import time
from urllib.parse import parse_qs, urlparse
import requests
from download import Download
class Douyin(object):
"""
抖音用户类
采集作品列表
"""
def __init__(self, param: str, limit: int = 0):
"""
初始化用户信息
参数自动判断：ID/URL
"""
self.limit = limit
self.http = requests.Session()
self.url = ''
self.type = 'unknow'
self.download_path = '暂未定义目录'
# ↑ 预定义属性，避免调用时未定义 ↑
self.param = param.strip()
self.sign = 'TG2uvBAbGAHzG19a.rniF0xtrq' # sign可以固定
self.__get_type() # 判断当前任务类型：链接/ID
self.aria2 = Download() # 初始化Aria2下载服务，先不指定目录了，在设置文件名的时候再加入目录
self.has_more = True
self.finish = False
# 字典格式方便入库用id做key/取值/修改对应数据，但是表格都接收数组
self.videosL = [] #列表格式
# self.videos = {} #字典格式
self.gids = {} # gid和作品序号映射
def __get_type(self):
"""
判断当前任务类型
链接/ID
"""
if '://' in self.param: # 链接
self.__url2redirect()
else: # ID
self.id = self.param
def __url2redirect(self):
"""
取302跳转地址
短连接转长链接
"""
headers = { # 以前作品需要解析去水印，要用到移动端UA，现在不用了
'User-Agent':
'Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1 Edg/89.0.4389.82'
}
try:
r = self.http.head(self.param, headers=headers, allow_redirects=False)
self.url = r.headers['Location']
except:
self.url = self.param
def __url2id(self):
try:
self.id = urlparse(self.url).path.split('/')[zxsq-anti-bbcode-3]
except:
self.id = ''
def __url2uid(self):
try:
query = urlparse(self.url).query
self.id = parse_qs(query)['sec_uid'][zxsq-anti-bbcode-0]
except:
self.id = ''
def get_sign(self):
"""
网页sign算法，现在不需要了，直接固定
"""
self.sign = 'TG2uvBAbGAHzG19a.rniF0xtrq'
return self.sign
def get_user_info(self):
"""
取用户信息
查询结果在 self.user_info
"""
if self.url:
self.__url2uid()
url = 'https://www.iesdouyin.com/web/api/v2/user/info/?sec_uid=' + self.id
try:
res = self.http.get(url).json()
info = res.get('user_info', dict())
except:
info = dict()
self.user_info = info
# 下载路径
username = '{}_{}_{}'.format(self.user_info.get('short_id', '0'),
self.user_info.get('nickname', '无昵称'), self.type)
self.download_path = Download.title2path(username) # 需提前处理非法字符串
def get_challenge_info(self):
"""
取话题挑战信息
查询结果在 self.challenge_info
"""
if self.url:
self.__url2id()
url = 'https://www.iesdouyin.com/web/api/v2/challenge/info/?ch_id=' + self.id
try:
res = self.http.get(url).json()
info = res.get('ch_info', dict())
except:
info = dict()
self.challenge_info = info
# 话题挑战下载路径
username = '{}_{}_{}'.format(self.challenge_info.get('cid', '0'),
self.challenge_info.get('cha_name', '无标题'), self.type)
self.download_path = Download.title2path(username) # 需提前处理非法字符串
def get_music_info(self):
"""
取音乐原声信息
查询结果在 self.music_info
"""
if self.url:
self.__url2id()
url = 'https://www.iesdouyin.com/web/api/v2/music/info/?music_id=' + self.id
try:
res = self.http.get(url).json()
info = res.get('music_info', dict())
except:
info = dict()
self.music_info = info
# 音乐原声下载路径
username = '{}_{}_{}'.format(self.music_info.get('mid', '0'), self.music_info.get('title', '无标题'),
self.type)
self.download_path = Download.title2path(username) # 需提前处理非法字符串
def crawling_users_post(self):
"""
采集用户作品
"""
self.type = 'post'
self.__crawling_user()
def crawling_users_like(self):
"""
采集用户喜欢
"""
self.type = 'like'
self.__crawling_user()
def crawling_challenge(self):
"""
采集话题挑战
"""
self.type = 'challenge'
self.get_challenge_info() # 取当前信息，用做下载目录
# https://www.iesdouyin.com/web/api/v2/challenge/aweme/?ch_id=1570693184929793&count=9&cursor=9&aid=1128&screen_limit=3&download_click_limit=0&_signature=AXN-GQAAYUTpqVxkCT6GHQFzfg
url = 'https://www.iesdouyin.com/web/api/v2/challenge/aweme/'
cursor = '0'
while self.has_more:
params = {
"ch_id": self.id,
"count": "21", # 可调大 初始值：9
"cursor": cursor,
"aid": "1128",
"screen_limit": "3",
"download_click_limit": "0",
"_signature": self.sign
}
try:
res = self.http.get(url, params=params).json()
cursor = res['cursor']
self.has_more = res['has_more']
self.__append_videos(res)
except:
print('话题挑战采集出错')
print('话题挑战采集完成')
def crawling_music(self):
"""
采集音乐原声
"""
self.type = 'music'
self.get_music_info() # 取当前信息，用做下载目录
# https://www.iesdouyin.com/web/api/v2/music/list/aweme/?music_id=6928362875564067592&count=9&cursor=18&aid=1128&screen_limit=3&download_click_limit=0&_signature=5ULmIQAAhRYNmMRcpDm2COVC5j
url = 'https://www.iesdouyin.com/web/api/v2/music/list/aweme/'
cursor = '0'
while self.has_more:
params = {
"music_id": self.id,
"count": "21", # 可调大 初始值：9
"cursor": cursor,
"aid": "1128",
"screen_limit": "3",
"download_click_limit": "0",
"_signature": self.sign
}
try:
res = self.http.get(url, params=params).json()
cursor = res['cursor']
self.has_more = res['has_more']
self.__append_videos(res)
except:
print('音乐原声采集出错')
print('音乐原声采集完成')
def __crawling_user(self):
"""
采集用户作品/喜欢
"""
self.get_user_info() # 取当前用户信息，昵称用做下载目录
max_cursor = 0
# https://www.iesdouyin.com/web/api/v2/aweme/like/?sec_uid=MS4wLjABAAAAaJO9L9M0scJ_njvXncvoFQj3ilCKW1qQkNGyDc2_5CQ&count=21&max_cursor=0&aid=1128&_signature=2QoRnQAAuXcx0DPg2DVICdkKEY&dytk=
# https://www.iesdouyin.com/web/api/v2/aweme/post/?sec_uid=MS4wLjABAAAAaJO9L9M0scJ_njvXncvoFQj3ilCKW1qQkNGyDc2_5CQ&count=21&max_cursor=0&aid=1128&_signature=DrXeeAAAbwPmb.wFM3e63w613m&dytk=
url = 'https://www.iesdouyin.com/web/api/v2/aweme/{}/'.format(self.type)
while self.has_more:
params = {
"sec_uid": self.id,
"count": "21",
"max_cursor": max_cursor,
"aid": "1128",
"_signature": self.sign,
"dytk": ""
}
try:
res = self.http.get(url, params=params).json()
max_cursor = res['max_cursor']
self.has_more = res['has_more']
self.__append_videos(res)
except:
print('作品采集出错')
print('作品采集完成')
def __append_videos(self, res):
"""
数据入库
"""
if res.get('aweme_list'):
for item in res['aweme_list']:
info = item['statistics']
info.pop('forward_count')
info.pop('play_count')
info['desc'] = Download.title2path(item['desc']) # 需提前处理非法字符串
info['uri'] = item['video']['play_addr']['uri']
info['play_addr'] = item['video']['play_addr']['url_list'][zxsq-anti-bbcode-0]
info['dynamic_cover'] = item['video']['dynamic_cover']['url_list'][zxsq-anti-bbcode-0]
info['status'] = 0 # 下载进度状态；等待下载：0，下载中：0.xx；下载完成：1
# 列表格式
self.videosL.append(info)
# 字典格式
# self.videos[info['aweme_id']] = info
# 此处可以直接添加下载任务，不过考虑到下载占用网速,影响采集过程，所以采集完再下载
if self.limit:
more = len(self.videos) - self.limit
if more >= 0:
# 如果给出了限制采集数目，超出的删除后直接返回
self.has_more = False
# 列表格式
self.videosL = self.videosL[:self.limit]
# 字典格式
# for i in range(more):
# self.videos.popitem()
# return
else: # 还有作品的情况下没返回数据则进入这里
print('未采集完成，但返回作品列表为空')
def download_all(self):
"""
作品抓取完成后，统一添加下载任务
可选择在外部注册回调函数，监听下载任务状态
"""
for id, video in enumerate(self.videosL):
# for id, video in self.videos.items():
gid = self.aria2.download(url=video['play_addr'],
filename='{}/{}_{}.mp4'.format(self.download_path, video['aweme_id'],
video['desc'])
# ,options={'gid': id} # 指定gid
)
self.gids[zxsq-anti-bbcode-gid] = id # 因为传入gid必须16位，所以就不指定gid了，另存一个字典映射
print('下载任务投递完成')| 欢迎光临 精易论坛 (https://125.confly.eu.org/) | Powered by Discuz! X3.4 |