Google Vision文本检测返回太多不必要的数据

from google.cloud import vision

client = vision.ImageAnnotatorClient()

# 加载图像
with open('path/to/your/image.jpg', 'rb') as image_file:
    content = image_file.read()

image = vision.Image(content=content)

# 进行文本检测
response = client.text_detection(image=image)

# 获取检测结果
texts = response.text_annotations

# 获取整个文本块
full_text = texts[0].description if texts else ""

# 获取单独的文本片段
individual_texts = [text.description for text in texts[1:]]

import re

# 示例：提取电子邮件地址
email_pattern = re.compile(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b')
emails = email_pattern.findall(full_text)

# 示例：提取电话号码
phone_pattern = re.compile(r'\b\d{3}[-.\s]??\d{3}[-.\s]??\d{4}\b')
phone_numbers = phone_pattern.findall(full_text)

print("Emails:", emails)
print("Phone Numbers:", phone_numbers)

image_context = vision.ImageContext(language_hints=['en'])

response = client.text_detection(image=image, image_context=image_context)
texts = response.text_annotations

if response.error.message:
    raise Exception(f'{response.error.message}')
else:
    texts = response.text_annotations
    if texts:
        full_text = texts[0].description
        individual_texts = [text.description for text in texts[1:]]
    else:
        full_text = ""
        individual_texts = []

from google.cloud import vision
import re

def detect_text(image_path):
    client = vision.ImageAnnotatorClient()

    with open(image_path, 'rb') as image_file:
        content = image_file.read()

    image = vision.Image(content=content)
    response = client.text_detection(image=image)

    if response.error.message:
        raise Exception(f'{response.error.message}')
    
    texts = response.text_annotations
    if not texts:
        return "", []

    full_text = texts[0].description
    individual_texts = [text.description for text in texts[1:]]

    return full_text, individual_texts

def extract_emails_and_phones(text):
    email_pattern = re.compile(r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b')
    phone_pattern = re.compile(r'\b\d{3}[-.\s]??\d{3}[-.\s]??\d{4}\b')

    emails = email_pattern.findall(text)
    phone_numbers = phone_pattern.findall(text)

    return emails, phone_numbers

# 使用示例
image_path = 'path/to/your/image.jpg'
full_text, individual_texts = detect_text(image_path)
emails, phone_numbers = extract_emails_and_phones(full_text)

print("Full Text:", full_text)
print("Individual Texts:", individual_texts)
print("Emails:", emails)
print("Phone Numbers:", phone_numbers)