zhang_crawl_bio/tests/mytest/get_suport_ua.py

# 支持的系统和浏览器品牌
supported_systems = ["Windows", "Linux", "Mac"]
supported_browsers = {
    "Chrome": 91,  # 假设 Chrome 的最低支持版本是 91
    "Firefox": 89,  # 假设 Firefox 的最低支持版本是 89
    "Safari": 14,  # 假设 Safari 的最低支持版本是 14
    "Edg": 91,  # 假设 Edge 的最低支持版本是 91
}

# 输入和输出文件路径
input_file = "K:/code/upwork/zhang_crawl_bio/mylib/user_agents.txt"
output_file = "K:/code/upwork/zhang_crawl_bio/mylib/filtered_user_agents.txt"

def extract_version(ua, browser):
    """
    从用户代理字符串中提取浏览器版本号
    """
    try:
        if browser == "Chrome":
            # Chrome 的版本号通常在 "Chrome/" 后面
            start = ua.find("Chrome/")
            if start == -1:
                return None
            start += len("Chrome/")
            # 提取直到非数字字符为止
            version_str = ""
            for char in ua[start:]:
                if char.isdigit():
                    version_str += char
                else:
                    break
            return int(version_str) if version_str else None
        elif browser == "Firefox":
            # Firefox 的版本号通常在 "Firefox/" 后面
            start = ua.find("Firefox/")
            if start == -1:
                return None
            start += len("Firefox/")
            # 提取直到非数字字符为止
            version_str = ""
            for char in ua[start:]:
                if char.isdigit():
                    version_str += char
                else:
                    break
            return int(version_str) if version_str else None
        elif browser == "Safari":
            # Safari 的版本号通常在 "Version/" 后面
            start = ua.find("Version/")
            if start == -1:
                return None
            start += len("Version/")
            # 提取直到非数字字符为止
            version_str = ""
            for char in ua[start:]:
                if char.isdigit():
                    version_str += char
                else:
                    break
            return int(version_str) if version_str else None
        elif browser == "Edg":
            # Edge 的版本号通常在 "Edg/" 后面
            start = ua.find("Edg/")
            if start == -1:
                return None
            start += len("Edg/")
            # 提取直到非数字字符为止
            version_str = ""
            for char in ua[start:]:
                if char.isdigit():
                    version_str += char
                else:
                    break
            return int(version_str) if version_str else None
    except Exception as e:
        print(f"Error extracting version from UA: {ua}, Error: {e}")
    return None

# 读取并过滤用户代理
with open(input_file, "r") as infile, open(output_file, "w") as outfile:
    for line in infile:
        line = line.strip()
        # 检查是否包含支持的系统和浏览器品牌
        if any(system in line for system in supported_systems):
            for browser, min_version in supported_browsers.items():
                if browser in line:
                    version = extract_version(line, browser)
                    if version is not None and version >= min_version:
                        outfile.write(line + "\n")
                        break

print(f"过滤后的用户代理已保存到 {output_file}")