testcase-data/Ours/get_content_wrong.py

import re

def contains_link_or_image(text):
    # 正则表达式匹配网页链接或图片链接
    url_pattern = r'(https?://[^\s]+)|(www\.[^\s]+)|([^\s]+\.jpg|[^\s]+\.png|[^\s]+\.gif|[^\s]+\.jpeg)'
    
    # 使用re.search判断是否匹配到链接
    if re.search(url_pattern, text):
        return True
    return False

def contains_html_tags(text):
    # 正则表达式匹配HTML标签
    html_tag_pattern = r'<[^>]+>'
    
    # 使用re.search判断是否匹配到HTML标签
    if re.search(html_tag_pattern, text):
        return True
    return False

import json
add_data = json.load(open("/home/i-luoxianzhen/data/TestCase-Gen/data/Ours/tcb_v7_add_data_no_en.jsonl", "r", encoding="utf-8"))

check_list = []
for item in add_data:
    tcb_id = item['tcb_id']
    content = item['query']
    if contains_html_tags(content) or contains_link_or_image(content):
        check_list.append(tcb_id)

print(f"包含 HTML 标签")
print("\n".join(check_list))