元气桌面单页面爬取

# 糖醋慕雨的快乐时光
import requests
import json
from openpyxl import load_workbook
from openpyxl import Workbook
import os

# 获取程序的绝对路径
current_directory = os.path.dirname(os.path.abspath(__file__))
# 创建douyin文件夹路径
douyin_folder = os.path.join(current_directory, "元气")
# 如果douyin文件夹不存在，则创建它
if not os.path.exists("元气"):
   os.mkdir("元气")

# 检查文件是否存在
file_path_xlsm = "yuan.xlsm"
if not os.path.exists(file_path_xlsm):
   print('not exists')
   # 创建一个工作簿
   wb = Workbook()
   # 保存为.xlsx文件
   wb.save(file_path_xlsm)
else:
   # 文件已存在，打开文件进行读取操作
   print('exists')

#     # 打开现有的.xlsx文件
# current_directory = os.path.dirname(os.path.abspath(__file__))
# file_path = os.path.join(current_directory,file_path_xlsm)
# wb = load_workbook(file_path)
wb = load_workbook(file_path_xlsm)
# 创建一个Workbook对象

# 选择或新建一个工作表
ws = wb.active

ws.cell(row=1, column=1, value="作者名")  # 作者名
ws.cell(row=1, column=2, value="作品名")  # 作品名
ws.cell(row=1, column=3, value="作品图片链接-封面")  # 作品图片链接
ws.cell(row=1, column=4, value="作品视频链接")  #  # 作品视频链接
ws.cell(row=1, column=5, value="作者主页链接")  # 作者主页链接
ws.cell(row=1, column=6, value="4k视频链接")  # 4k视频链接
ws.cell(row=1, column=7, value="作品上传时间")  # 作品上传时间


dwid = input('请输入url地址:')
dwid = int(dwid.split('=')[1])

detail_params = {
   'wid': dwid,
   'common': {'player_version': 0}
}

headers = {
   'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
   'accept-language': 'zh-CN,zh;q=0.9',
   'accept-encoding': 'gzip, deflate, br',
   'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
}

detail_url = 'https://pcwallpaper.zhhainiao.com/wallpaper/live/detail' #


# 获取页面html
def scrape_Main(url,headers,detail_params):
   response = requests.post(url, headers=headers,json=detail_params)
   try:
       if response.status_code == 200:
           response.encoding = response.apparent_encoding
           # print(response.text)/
           return response.text
   except requests.RequestException:
       print('请求失败')

html = scrape_Main(detail_url,headers,detail_params)
# author_uid = json.loads(html)  # 作者独有的uid
# print(author_uid)  # 41424485
data = json.loads(html)['data']
# print(data)
preview_video = data['preview_video']  # 视频链接
update_time = data['update_time']  # 更新时间- 上传时间
preview_jpg = data['preview_jpg'].split('?')[0]  # 图片链接
author = 'https://wp.cheetahfun.com/personal/author?author_uid=' + str(data['author_uid'])  # 作者主页链接
video_4k = data['video_4k']  # 我打不开, 应该是4k 视频
author_name = data['author_name']  # 作者名
wname = data['wname']  # 作品名



# 获取最后一行的行号
last_row = ws.max_row
ws.cell(row=last_row + 1, column=1, value=author_name)  # 作者名
ws.cell(row=last_row + 1, column=2, value=wname)        # 作品名
ws.cell(row=last_row + 1, column=3, value=preview_jpg)  # 作品图片链接
ws.cell(row=last_row + 1, column=4, value=preview_video)  # 作品视频链接
ws.cell(row=last_row + 1, column=5, value=author)  # 作者主页链接
ws.cell(row=last_row + 1, column=6, value=video_4k)  # 4k视频链接
ws.cell(row=last_row + 1, column=7, value=update_time)  # 作品上传时间

with open('yuan.txt', 'w', encoding='utf-8') as f:
   f.write("作者名:{}\n作品名:{}\n作者主页:{}\n作品视频:{}\n图片链接:{}\n作品上传时间:{}\n".format(author_name, wname, author,preview_video,preview_jpg,update_time))
print(' {}:  数据已保存在yuan.txt文件下'.format(wname))
# 冻结首行
ws.freeze_panes = 'A2'
# 保存文件
wb.save(file_path_xlsm)

# 创建"元气\\wname\\"文件夹路径
douyin_folder = os.path.join("元气\\", f"{wname}\\")
# 如果"元气\\wname\\"文件夹不存在，则创建它
if not os.path.exists(douyin_folder):
   os.mkdir(douyin_folder)

Video = requests.get(preview_video).content
with open('元气\\' +  f'{wname}\\'+ wname + '.mp4', mode='wb+') as f:
   f.write(Video)
   print(wname + ': 视频下载完成')

preview_jpg = requests.get(preview_jpg).content
with open('元气\\' + f'{wname}\\'+ wname + '.jpg', mode='wb+') as f:
   f.write(preview_jpg)
   print(wname + ': 图片下载完成')

print('作品: {} 保存成功'.format(wname))

import pandas as pd

# 读取Excel文件
df = pd.read_excel(file_path_xlsm)

# 使用drop_duplicates方法去重
df_deduplicated = df.drop_duplicates()

# 将去重后的DataFrame保存回Excel
df_deduplicated.to_excel(file_path_xlsm, index=False)

   # 打开现有的.xlsx文件
# current_directory = os.path.dirname(os.path.abspath(__file__))
# file_path = os.path.join(current_directory, file_path_xlsm)
wb = load_workbook(file_path_xlsm)
# 选择或新建一个工作表
ws = wb.active
# 冻结首行
ws.freeze_panes = 'A2'
# 保存文件
wb.save(file_path_xlsm)

print('数据去重成功')

# 测试: https://wp.cheetahfun.com/personal/wallpaper?dwid=180048