使用tweepy和tesseract提取tweet中的img并获取文本

import tweepy
import requests
import pytesseract
from PIL import Image

# Twitter API认证和授权
consumer_key = 'YOUR_CONSUMER_KEY'
consumer_secret = 'YOUR_CONSUMER_SECRET'
access_token = 'YOUR_ACCESS_TOKEN'
access_token_secret = 'YOUR_ACCESS_TOKEN_SECRET'

auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)

api = tweepy.API(auth)

# 搜索相关的tweets
search_query = 'YOUR_SEARCH_QUERY'
tweets = api.search(q=search_query)

# 遍历搜索结果
for tweet in tweets:
    # 检查tweet是否包含图片
    if 'media' in tweet.entities:
        # 获取图片的URL
        media_url = tweet.entities['media'][0]['media_url']
        
        # 下载图片并保存到本地
        image_data = requests.get(media_url).content
        with open('image.jpg', 'wb') as f:
            f.write(image_data)
        
        # 使用tesseract进行OCR，提取文本
        image = Image.open('image.jpg')
        text = pytesseract.image_to_string(image)
        
        # 打印提取到的文本
        print(text)