Python采集网站VIP文档，实现图片文字识别，并保存word格式！

python 3.8
pycharm

requests --> pip install requests
re
base64
docx --> pip install python-docx

doc = Document()
 
 
def Content(content):
    url = "https://aip.baidubce.com/oauth/2.0/token?grant_type=client_credentials&client_id=xxxx&client_secret=xxxx"
    payload = ""
    headers = {
        'Content-Type': 'application/json',
        'Accept': 'application/json'
    }
    response = requests.request("POST", url, headers=headers, data=payload)
    access_token = response.json()['access_token']

    request_url = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate_basic"
    # 二进制方式打开图片文件
    # 完整源码和视频讲解都打包好
    # 放在这个Q裙了：708525271 
    # f = open('img\\1 计算机概述1.jpg', 'rb')
    img = base64.b64encode(content)
    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()
    words_result = '\n'.join([i['words'] for i in json_data['words_result']])
    print(words_result)

# 模拟浏览器 --> 字典数据类型 --> 键:值
headers = {
    # User-Agent 用户代理 表示浏览器基本身份信息
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36'
}
# 请求链接
url = 'https://www.docin.com/p-3282300896.html'
# 发送请求
response = requests.get(url=url, headers=headers)

# 获取网页数据
html_data = response.text
# 提取sid参数
sid = re.findall('flash_param_hzq:"(.*?)",', html_data)[0]
# 提取名字
name = re.findall('productName:"(.*?)",', html_data)[0]
# 提取页码
num = re.findall('<em>(\d+)</em>页</span>', html_data)[0]
# 构建完整图片链接
content_list = []
for page in range(1, int(num)+1):
    # 字符串格式化方法
    img = f'http://221.122.117.73/docinpic.jsp?sid={sid}&file=3282300896&width=942&pageno={page}'

# 发送请求, 获取二进制数据<图片内容>
img_content = requests.get(url=img, headers=headers).content
words = Content(img_content)
doc.add_paragraph(words)