代码拉取完成,页面将自动刷新
同步操作将从 yanqiang/python爬虫记录 强制同步,此操作会覆盖自 Fork 仓库以来所做的任何修改,且无法恢复!!!
确定后同步将在后台操作,完成时将刷新页面,请耐心等待。
# -*- coding: utf-8 -*-
# @Time : 2021/6/25 15:25
# @Description:
# @Author : YanQiang
# @Email : 18988775754@163.com
# @File : douyin.py
import requests
import json
import os
import time
import re
"""
1.根据用户页面分享的字符串提取短url
2.根据短url加上302获取location,提取sec_id
3.拼接视频列表请求url
params = {
'sec_uid' : 'MS4wLjABAAAAbtSlJK_BfUcuqyy8ypNouqEH7outUXePTYEcAIpY9rk',
'count' : '200',
'min_cursor' : '1612108800000',
'max_cursor' : '1619251716404',
'aid' : '1128',
'_signature' : 'PtCNCgAAXljWCq93QOKsFT7QjR'
}
"""
headers = {
"user-agent": "Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.114 Mobile Safari/537.36"
}
# string = '在抖音,记录美好生活! https://v.douyin.com/ekkTsYw/'
# string = input('粘贴分享链接:')
shroturl = "https://v.douyin.com/e4Yc8G7/"
# shroturl = re.findall('[a-z]+://[\S]+', string, re.I | re.M)[0]
print(shroturl)
startpage = requests.get(url=shroturl, headers=headers, allow_redirects=False)
location = startpage.headers['location']
sec_uid = re.findall('(?<=sec_uid=)[a-z,A-Z,0-9, _, -]+', location, re.M | re.I)[0]
getname = requests.get(url='https://www.iesdouyin.com/web/api/v2/user/info/?sec_uid={}'.format(sec_uid),
headers=headers).text
userinfo = json.loads(getname)
name = userinfo['user_info']['nickname']
print(userinfo['user_info']['nickname'])
Path = name
if os.path.exists(path=Path) == False:
os.mkdir(path=Path)
else:
print('directory exist')
os.chdir(path=Path)
"""new function"""
year = ('2018', '2019', '2020', '2021')
month = ('01', '02', '03', '04', '05', '06', '07', '08', '09', '10', '11', '12')
timepool = [x + '-' + y + '-01 00:00:00' for x in year for y in month]
print(timepool)
exit()
k = len(timepool)
for i in range(k):
if i < k - 1:
print('begintime=' + timepool[i])
print('endtime=' + timepool[i + 1])
beginarray = time.strptime(timepool[i], "%Y-%m-%d %H:%M:%S")
endarray = time.strptime(timepool[i + 1], "%Y-%m-%d %H:%M:%S")
t1 = int(time.mktime(beginarray) * 1000)
t2 = int(time.mktime(endarray) * 1000)
print(t1, t2)
params = {
'sec_uid': sec_uid,
'count': 200,
'min_cursor': t1,
'max_cursor': t2,
'aid': 1128,
'_signature': 'PtCNCgAAXljWCq93QOKsFT7QjR'
}
awemeurl = 'https://www.iesdouyin.com/web/api/v2/aweme/post/?'
awemehtml = requests.get(url=awemeurl, params=params, headers=headers).text
data = json.loads(awemehtml)
# print(data)
# print(type(data))
awemenum = len(data['aweme_list'])
print(awemenum)
for i in range(awemenum):
videotitle = data['aweme_list'][i]['desc'].replace("?", "").replace("\"", "").replace(":", "")
videourl = data['aweme_list'][i]['video']['play_addr']['url_list'][0]
start = time.time()
print('{} ===>downloading'.format(videotitle))
with open(videotitle + '.mp4', 'wb') as v:
try:
v.write(requests.get(url=videourl, headers=headers).content)
end = time.time()
cost = end - start
print('{} ===>downloaded ===>cost {}s'.format(videotitle, cost))
except Exception as e:
print('download error')
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。