前言
主要是为了抖音短视频：带水印视频链接、不带水印的视频链接、视频文案、作者信息
代码
如果不进行数据库相关操作，可以将
from pymysql import * # 引入数据库依赖
from pymysql.converters import escape_string # 入库字符转义
这两个依赖干掉
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
| import re
import json
import requests
import webbrowser
from pymysql import *
from pymysql.converters import escape_string
def getDouyinUrlByShareUrl(douyinShareUrl):
headers = {
'user-agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.114 Mobile Safari/537.36 Edg/103.0.1264.62'
}
ree = requests.get(douyinShareUrl, headers=headers)
new_url = ree.url
id = re.search(r'/video/(.*?)/', new_url).group(1)
url = 'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo/?item_ids=' + id
ree = requests.get(url, headers=headers)
wm = ree.json()
result = wm['item_list'][0]['video']['play_addr']['url_list'][0].replace('wm', '')
print("视频无水印url：" + result)
return result
def get_url(content):
if len(re.findall('[a-z]+://[\S]+', content, re.I | re.M)) > 0:
return re.findall('[a-z]+://[\S]+', content, re.I | re.M)[0]
return None
def getRedirectUrl(url, header):
response = requests.get(url, headers=header)
return response.url
def getDouyinVideoInfo(douyinShareUrl):
douyinLink = 'https://www.iesdouyin.com/web/api/v2/aweme/iteminfo'
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/92.0.4515.107 Safari/537.36'}
if douyinLink.strip() is not None:
if get_url(douyinShareUrl) is not None:
realUrl = getRedirectUrl(get_url(douyinShareUrl), headers)
startUrl = realUrl[0:realUrl.index('?')]
id = startUrl[startUrl.rindex('/') + 1:len(startUrl)]
douyinParams = {'item_ids': id}
if realUrl.__contains__('www.douyin.com/video'):
douyinResponse = requests.get(url=douyinLink, params=douyinParams, headers=headers)
body = douyinResponse.text
data = json.loads(body)
print("用户信息：" + data)
try:
videoTitle = data['item_list'][0]['desc']
videoUrl = data['item_list'][0]['video']['play_addr']['url_list'][0]
realVideoUrl = f'{videoUrl}'.replace('playwm', 'play')
print("视频文案：" + videoTitle)
print("视频带水印url：" + videoUrl)
print("视频无水印url：" + realVideoUrl)
return realVideoUrl
except Exception as e:
print(e)
if __name__ == '__main__':
url = 'https://v.douyin.com/jUAfreu/'
print(getDouyinUrlByShareUrl("https://v.douyin.com/jUAfreu/"))
print(" ======================================================= ")
print(getDouyinVideoInfo("https://v.douyin.com/jUAfreu/"))
print(" ======================================================= ")
|
如果链接中包含其他文字，可以通过下面这种方式将网站的url解析出来
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
|
import re
def getUrlNoSuffix(str):
urls = re.findall('https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+', str)
return urls
def getUrl(str):
regex = r"(?i)\b((?:https?://|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s`!()\[\]{};:'\".,<>?«»“”‘’]))"
url = re.findall(regex, str)
return [x[0] for x in url]
if __name__ == '__main__':
shareUrl = '锄禾日当午，汗滴禾下土 https://image.baidu.com/search/index/ 谁知盘中餐，粒粒皆辛苦'
print("Urls: ", getUrl(shareUrl))
|
微信
支付宝
