利用github的Actions,每天爬取bing壁纸上传的百度网盘

Editor

1. import requests
   
2. import base64
   
3. from datetime import datetime
   
4. from datetime import timedelta
   
5. from datetime import timezone
   
6. from bs4 import BeautifulSoup
   
7. import time
   
8. import ddddocr
   
9. import os
   
10. baidu_cookie = os.environ["BAIDU_COOKIE"]
    
11. 
    
12. SHA_TZ = timezone(
    
13.     timedelta(hours=8),
    
14.     name='Asia/Shanghai',
    
15. )
    
16. utc_now = datetime.utcnow().replace(tzinfo=timezone.utc)
    
17. beijing_now = utc_now.astimezone(SHA_TZ)
    
18. 
    
19. 
    
20. # 定义headers
    
21. headers = {
    
22.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.110 Safari/537.36',
    
23. }
    
24. # 定义baidu_headers,cookie需要 BAIDUID  BDUSS ,STOKEN
    
25. baidu_headers = {
    
26.      "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/"
    
27.                   "97.0.4692.99 Safari/537.36 Edg/97.0.1072.69",
    
28.     "Referer": "https://pan.baidu.com/disk/home?from=newversion&stayAtHome=true",
    
29.     "cookie": baidu_cookie,
    
30.     'Connection': 'close'
    
31. }
    
32. 
    
33. 
    
34. # 获取bing每日一图
    
35. def get_bing_pic():
    
36.     url = 'https://cn.bing.com/'
    
37.     r = requests.get(url, headers=headers)
    
38.     soup = BeautifulSoup(r.text, 'html.parser')
    
39.     # 寻找link标签,preloadBg图片的url
    
40.     link = soup.find('link', id='preloadBg')
    
41.     # 获取图片url
    
42.     img_url = link['href']
    
43.     # 分割url通过&分割
    
44.     img_url = img_url.split('&')[0]
    
45.     # 判断url是否有'1920x1080' 如果有则替换为'UHD',UHD为4K图片标识
    
46.     if '1920x1080' in img_url:
    
47.         img_url = img_url.replace('1920x1080', 'UHD')
    
48.         img_url = "https://s.cn.bing.net" + img_url
    
49.     # 获取图片名称
    
50.     img_name = img_url.split('=')[1]
    
51.     # 返回图片url
    
52.     return img_url, img_name
    
53. 
    
54. 
    
55. # 判断网盘是否登录
    
56. def is_login():
    
57.     url = 'https://pan.baidu.com/disk/home?from=newversion&stayAtHome=true#/all?path=%2F&vmode=list'
    
58.     r = requests.get(url, headers=baidu_headers)
    
59.     # 通过网页源码判断是否登录
    
60.     if '百度网盘-全部文件' in r.text:
    
61.         print('网盘登录成功')
    
62.         return True
    
63.     else:
    
64.         print("更换COOKIE")
    
65.         return False
    
66. 
    
67. 
    
68. # 获取logid,bdstoken
    
69. def get_logid_bdstoken():
    
70.     # 获取bdstoken的url
    
71.     get_bdstoken_url = "http://pan.baidu.com/api/gettemplatevariable?clienttype=0&app_id=250528&web=1&fields=[%22bdstoken%22]"
    
72.     bdstoken = requests.get(get_bdstoken_url, headers=baidu_headers).json().get('result').get('bdstoken')
    
73.     # 获取logid
    
74.     logid = str(base64.b64encode(
    
75.         requests.get(get_bdstoken_url, headers=baidu_headers).request.headers.get('cookie').split(';')[0].strip(
    
76.             "BAIDUID=").encode(
    
77.             'utf-8'))).replace("b'", "").replace("'", "")
    
78.     return logid, bdstoken
    
79. 
    
80. # 验证网盘目标目录文件夹是否存在
    
81. def is_dir_exist(logid, bdstoken):
    
82.     url = f"https://pan.baidu.com/api/list?clienttype=0&app_id=250528&web=1&dp-logid={logid}&order=time&desc=1&dir=/图片&num=100&page=1"
    
83.     url1 = f"https://pan.baidu.com/api/create?a=commit&channel=chunlei&web=1&app_id=250528&bdstoken={bdstoken}&logid={logid}&clienttype=0"
    
84.     data = {
    
85.         "path": "/图片/" + str(beijing_now.date()),
    
86.         "isdir": 1,
    
87.         'block_list': []
    
88.     }
    
89.     r = requests.get(url, headers=baidu_headers)
    
90.     for i in r.json().get('list'):
    
91.         if str(beijing_now.date()) in i.get('server_filename'):
    
92.             return True
    
93.         else:
    
94.             requests.post(url1, headers=baidu_headers, data=data)
    
95.             return is_dir_exist(logid, bdstoken)
    
96. def is_file_exist(logid, img_name):
    
97.     url = f"https://pan.baidu.com/api/list?clienttype=0&app_id=250528&web=1&dp-logid={logid}&order=time&desc=1&dir=/图片/{str(beijing_now.date())}&num=100&page=1"
    
98.     # 发送请求
    
99.     r = requests.get(url=url, headers=baidu_headers)
    
100.     # 判断是否下载成功
     
101.     if len(r.json().get("list")) == 0:
     
102.         print("今日未下载")
     
103.         return True
     
104.     for i in r.json().get('list'):
     
105.         if img_name in i.get('path'):
     
106.             print('今天图片下载完成')
     
107.             return False
     
108. 
     
109. # 网盘离线下载,参数为logid,bdstoken,图片url
     
110. def download_offline(logid, bdstoken, img_url):
     
111.     # 拼接网盘离线下载url
     
112.     download_offline_url = f"https://pan.baidu.com/rest/2.0/services/cloud_dl?channel=chunlei&web=1&app_id=250528&bdstoken={bdstoken}&logid={logid}&clienttype=0"
     
113.     # 定义data
     
114.     data = {
     
115.         "method": "add_task",
     
116.         "app_id": "250528",
     
117.         "source_url": img_url,
     
118.         "save_path": f"/图片/{str(beijing_now.date())}"  # 网盘目录
     
119.     }
     
120.     # 发送请求
     
121.     r = requests.post(download_offline_url, headers=baidu_headers, data=data)
     
122.     if "Invalid source url" in r.json():
     
123.         print("重新下载 下载地址无效，请核对")
     
124.         download_offline(logid, bdstoken, img_url)
     
125.     if 'vcode' in r.json():
     
126.         print("需要验证码调用")
     
127.         download_offline_captcha(logid, bdstoken, img_url, r)
     
128. 
     
129. 
     
130. # 需要验证码的离线下载
     
131. def download_offline_captcha(logid, bdstoken, img_url, request):
     
132.     # 拼接网盘离线下载url
     
133.     download_offline_url = f"https://pan.baidu.com/rest/2.0/services/cloud_dl?channel=chunlei&web=1&app_id=250528&bdstoken={bdstoken}&logid={logid}&clienttype=0"
     
134.     # 通过ddddocr库识别验证码
     
135.     ocr = ddddocr.DdddOcr()
     
136.     # 验证码图片
     
137.     captcha_img = requests.get(request.json()['img'], headers=baidu_headers).content
     
138.     # 验证码ocr
     
139.     captcha = ocr.classification(captcha_img)
     
140.     print(captcha)
     
141. 
     
142.     # 定义data
     
143.     data = {
     
144.         "method": "add_task",
     
145.         "app_id": "250528",
     
146.         "source_url": img_url,
     
147.         "save_path": f"/图片/{str(beijing_now.date())}",  # 网盘目录
     
148.         "input": captcha,
     
149.         "vcode": request.json()['vcode']
     
150. 
     
151.     }
     
152.     # 发送请求
     
153.     r = requests.post(download_offline_url, headers=baidu_headers, data=data)
     
154.     print(r.json())
     
155.     if 'vcode' in r.json():
     
156.         time.sleep(3)
     
157.         print('重新验证')
     
158.         download_offline_captcha(logid, bdstoken, img_url, request)
     
159. 
     
160. 
     
161. # 判断是否下载成功
     
162. def is_download_success(logid, img_name):
     
163.     time.sleep(2)
     
164.     # 拼接判断是否下载成功的url
     
165.     url = f"https://pan.baidu.com/api/list?clienttype=0&app_id=250528&web=1&dp-logid={logid}&order=time&desc=1&dir=/图片/{str(beijing_now.date())}&num=100&page=1"
     
166.     # 发送请求
     
167.     r = requests.get(url, headers=baidu_headers)
     
168. 
     
169.     # 判断是否下载成功
     
170.     if len(r.json().get("list")) == 0:
     
171.         print("未下载完成")
     
172.         time.sleep(2)
     
173.         return is_download_success(logid, img_name)
     
174.     for ii in r.json().get('list'):
     
175.         if img_name in ii.get('path'):
     
176.             print('今天图片下载完成')
     
177.             return False
     
178.     for i in r.json().get('list'):
     
179.         if "th.jpg" in i.get('path'):
     
180.             print('下载完成')
     
181.             return True
     
182.         else:
     
183.             print(i)
     
184.             print("有其他图片,继续下载")
     
185.     return is_download_success(logid, img_name)
     
186. 
     
187. 
     
188. def rechristen(logid, bdstoken, img_name):
     
189.     # 拼接改名url
     
190.     name_url = f"https://pan.baidu.com/api/filemanager?opera=rename&async=2&onnest=fail&channel=chunlei&web=1&app_id=250528&bdstoken={bdstoken}&logid={logid}&clienttype=0"
     
191.     # 定义data
     
192.     data = {
     
193.         "filelist": '[{"path":"' + f"/图片/{str(beijing_now.date())}" + '/th.jpg","newname":"' + img_name + '"}]'
     
194.     }
     
195.     # 发送请求
     
196.     requests.post(name_url, data, headers=baidu_headers)
     
197.     print("改名完成")
     
198. 
     
199. 
     
200. if __name__ == '__main__':
     
201.     img_url, img_name = get_bing_pic()
     
202.     if is_login():
     
203.         logid, bdstoken = get_logid_bdstoken()
     
204.         if is_dir_exist(logid, bdstoken) and is_file_exist(logid, img_name):
     
205.             download_offline(logid, bdstoken, img_url)
     
206.             if is_download_success(logid, img_name):
     
207.                 rechristen(logid, bdstoken, img_name)

复制代码

123456823

论坛不能没有像楼主这样的人才啊！我会一直支持知鸟论坛。

幸福341

楼主发贴辛苦了，谢谢楼主分享！我觉得知鸟论坛是注册对了！

风来时狂放

我看不错噢 谢谢楼主！知鸟论坛越来越好！

dxf17

这东西我收了！谢谢楼主！知鸟论坛真好！

贺老师

论坛不能没有像楼主这样的人才啊！我会一直支持知鸟论坛。

六翼天使494

这东西我收了！谢谢楼主！知鸟论坛真好！

永远爱你冰塘

论坛不能没有像楼主这样的人才啊！我会一直支持知鸟论坛。

心随674

其实我一直觉得楼主的品味不错！呵呵！知鸟论坛太棒了！

永远就三年疗

感谢楼主的无私分享！要想知鸟论坛好 就靠你我他