# 導(dǎo)入數(shù)據(jù)請(qǐng)求模塊
import requests
# 導(dǎo)入格式化輸出模塊
from pprint import pprint
# 導(dǎo)入base64
import base64
# 導(dǎo)入os模塊
import os
# 導(dǎo)入文檔模塊
from docx import Document
# 導(dǎo)入正則
import re
# 導(dǎo)入json
import json

def get_content(file):
    # client_id 為官網(wǎng)獲取的AK， client_secret 為官網(wǎng)獲取的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']
    '''
    通用文字識(shí)別（高精度版）
    '''
    request_url = "https://aip.****.com/rest/2.0/ocr/v1/accurate_basic"
    # 二進(jìn)制方式打開(kāi)圖片文件
    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()
    # 列表推導(dǎo)式
    words = '\n'.join([i['words'] for i in json_data['words_result']])
    return words

# # 讀取文件夾里面所有圖片內(nèi)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文檔里面
# doc = Document()
# # 添加第一段文檔內(nèi)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'
# 請(qǐng)求頭
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'] # 評(píng)分
    viewCount = j['viewCount'] # 閱讀量
    downloadCount = j['downloadCount'] # 下載量
    docId = j['docId'] # 數(shù)據(jù)包ID

    # 確定請(qǐng)求鏈接
    url = 'https://wenku.****.com/gsearch/rec/pcviewdocrec'
    # 請(qǐng)求參數(shù)
    data = {
        'docId': docId,
        'query': name,
        'recPositions': ''
    }
    # 請(qǐng)求頭
    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'
    }
    #發(fā)送請(qǐng)求
    response = requests.get(url=url, params=data, headers=headers)
    # <Response [200]> 響應(yīng)對(duì)象, 200 表示請(qǐng)求成功
    print(response)

    # 定義文件名 整型
    num = 1
    # for循環(huán)遍歷, 把列表里面元素一個(gè)一個(gè)提取出來(lái)
    for index in response.json()['data']['relateDoc']:
        # index 字典呀
        pic = index['pic']
        print(pic)

        # # 4. 保存數(shù)據(jù)  發(fā)送請(qǐng)求 + 獲取數(shù)據(jù) 二進(jìn)制數(shù)據(jù)內(nèi)容
        # img_content = requests.get(url=pic, headers=headers).content
        # # 'img\\'<文件夾名字> + str(num)<文件名> + '.jpg'<文件后綴>  mode='wb' 保存方式, 二進(jìn)制保存
        # # str(num) 強(qiáng)制轉(zhuǎn)換成 字符串
        # # '圖片\\' 相對(duì)路徑, 相對(duì)于你代碼的路徑 你代碼在那個(gè)地方, 那個(gè)代碼所在地方圖片文件夾
        # with open('圖片\\' + str(num) + '.jpg', mode='wb') as f:
        #     # 寫(xiě)入數(shù)據(jù) 保存數(shù)據(jù)  把圖片二進(jìn)制數(shù)據(jù)保存
        #     f.write(img_content)
        # # 每次循環(huán) + 1
        # print(num)
        # num += 1