gameui/ocr
2
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Refactor download_image function and add print

Browse Source 
statement for image OCR results
This commit is contained in:
觉
2023-11-16 07:31:19 +08:00
parent 627300d8fd
commit 65689e3df5
1 changed files with 2 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
main.py
View File

@@ -11,7 +11,7 @@ config = dotenv_values(".env")
ImageFile.LOAD_TRUNCATED_IMAGES = True ImageFile.LOAD_TRUNCATED_IMAGES = True
# 下载图片(使用OSS下载) # 下载图片(使用OSS下载)
def download_image(url:str) -> Image: def download_image(url:str) -> Image.Image:
if url.startswith('http://image.gameuiux.cn/') or url.startswith('https://image.gameuiux.cn/'): if url.startswith('http://image.gameuiux.cn/') or url.startswith('https://image.gameuiux.cn/'):
try: try:
url = url.replace('http://image.gameuiux.cn/', '').replace('https://image.gameuiux.cn/', '') url = url.replace('http://image.gameuiux.cn/', '').replace('https://image.gameuiux.cn/', '')
@@ -42,7 +42,6 @@ cursor.execute("SELECT id, content FROM web_images LIMIT 5")
# 获取查询结果 # 获取查询结果
rows = cursor.fetchall() rows = cursor.fetchall()
for row in rows: for row in rows:
#print(row)
image = download_image(row['content']) image = download_image(row['content'])
if image is None: if image is None:
print('图片下载失败，跳过') print('图片下载失败，跳过')
@@ -50,7 +49,7 @@ for row in rows:
out = ocr.ocr(image) out = ocr.ocr(image)
# 这段代码将只包含那些非空、不是纯数字且长度大于1的'text'值 # 这段代码将只包含那些非空、不是纯数字且长度大于1的'text'值
texts = [item['text'] for item in out if item['text'] and not item['text'].isdigit() and len(item['text']) > 1] texts = [item['text'] for item in out if item['text'] and not item['text'].isdigit() and len(item['text']) > 1]
print(texts) print(row['id'], texts)
# 关闭游标和连接 # 关闭游标和连接