Python实现复制文档数据

# 导入数据请求模块
import requests
# 导入格式化输出模块
from pprint import pprint
# 导入base64
import base64
# 导入os模块
import os
# 导入文档模块
from docx import Document
# 导入正则
import re
# 导入JSON
import json

def get_content(file):
    # client_id 为官网获取的AK， client_secret 为官网获取的SK
    host = 'https://aip.****.com/oauth/2.0/token?grant_type=client_credentials&client_id=Gu7BGsfoKFZjLGvOKP7WezYv&client_secret=rGa2v2FcVnxBDFlerSW5H0D2eO7nRxdp'
    response = requests.get(host)
    access_token = response.json()['access_token']
    '''
    通用文字识别（高精度版）
    '''
    request_url = "Https://aip.****.com/rest/2.0/ocr/v1/accurate_basic"
    # 二进制方式打开图片文件
    f = open(file, 'rb')
    img = base64.b64encode(f.read())
    params = {"image":img}
    request_url = request_url + "?access_token=" + access_token
    headers = {'content-type': 'application/x-www-fORM-urlencoded'}
    json_data = requests.post(request_url, data=params, headers=headers).json()
    # 列表推导式
    words = '\n'.join([i['words'] for i in json_data['words_result']])
    return words

# # 读取文件夹里面所有图片内容
# content_list = []
# files = os.listdir('img\\')
# for file in files:
#     filename = 'img\\' + file
#     words = get_content(file=filename)
#     print(words)
#     content_list.append(words)
#
# # 保存word文档里面
# doc = Document()
# # 添加第一段文档内容
# content = '\n'.join(content_list)
# doc.add_paragraph(content)
# doc.save('data.docx')

link = 'https://wenku.****.com/aggs/74d1a923482fb4daa58d4b8e?index=0&_wkts_=1670327737660&bdQuery=%E7%AD%94%E9%A2%98'
# 请求头
headers = {
    'User-Agent': 'Mozilla/5.0 (windows NT 10.0; WOW64) AppleWEBKit/537.36 (Khtml, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}
html_data = requests.get(url=link, headers=headers).text
json_data = json.loads(re.findall('var pageData = (.*?);', html_data)[0])
pprint(json_data)
for j in json_data['aggInfo']['docList']:
    name = j['title']  # 名字
    score = j['score'] # 评分
    viewCount = j['viewCount'] # 阅读量
    downloadCount = j['downloadCount'] # 下载量
    docId = j['docId'] # 数据包ID

    # 确定请求链接
    url = 'https://wenku.****.com/gsearch/rec/pcviewdocrec'
    # 请求参数
    data = {
        'docId': docId,
        'query': name,
        'recPositions': ''
    }
    # 请求头
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
    }
    #发送请求
    response = requests.get(url=url, params=data, headers=headers)
    # <Response [200]> 响应对象, 200 表示请求成功
    print(response)

    # 定义文件名 整型
    num = 1
    # for循环遍历, 把列表里面元素一个一个提取出来
    for index in response.json()['data']['relateDoc']:
        # index 字典呀
        pic = index['pic']
        print(pic)

        # # 4. 保存数据  发送请求 + 获取数据 二进制数据内容
        # img_content = requests.get(url=pic, headers=headers).content
        # # 'img\\'<文件夹名字> + str(num)<文件名> + '.jpg'<文件后缀>  mode='wb' 保存方式, 二进制保存
        # # str(num) 强制转换成 字符串
        # # '图片\\' 相对路径, 相对于你代码的路径 你代码在那个地方, 那个代码所在地方图片文件夹
        # with open('图片\\' + str(num) + '.jpg', mode='wb') as f:
        #     # 写入数据 保存数据  把图片二进制数据保存
        #     f.write(img_content)
        # # 每次循环 + 1
        # print(num)
        # num += 1