Mission/huiduw/m3.1

works/huiduw/M1.1/cf_spider.py

@@ -0,0 +1,47 @@
+import requests
+import json
+import sys
+from lxml import etree
+def get_user_info(username):
+    #链接构造
+    url ='https://codeforces.com/profile/{}/'.format(username)
+    #伪装header
+    headers = {
+        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0"
+    }
+    res = requests.get(url,headers)
+    if res.status_code == 200:
+        f = 0
+        text = res.content.decode('utf-8')
+        html = etree.HTML(text)
+        try:
+            rank = html.xpath("//div[@class='user-rank']/span[@class='user-legendary']/text()")[0]
+        except Exception as e:
+            sys.stderr.write("No such handle")
+            sys.exit(1)
+
+        try:
+            rating = html.xpath("//div[@class='info']/ul[1]/li[1]/span[1]/text()")[0]
+        except Exception as e:
+            #标记无rating记录
+            f = 1
+        if(f == 1):
+            user_info = {
+                "handle":username
+            }
+        else:
+            user_info ={
+                "handle":username,
+                "rating":rating,
+                "rank":rank[:-1] #去除最后一位空格
+            }
+        res_json = json.dumps(user_info)
+        sys.stdout.write(res_json)
+        sys.exit(0)
+    else:
+        sys.stderr.write("network anomaly")
+
+if __name__ == '__main__':
+    username = sys.argv[1:][0]
+    # username = input()
+    get_user_info(username)

works/huiduw/M1.1/record.md

@@ -0,0 +1,58 @@
+# code
+
+```python
+import requests
+import json
+import sys
+from lxml import etree
+def get_user_info(username):
+    #链接构造
+    url ='https://codeforces.com/profile/{}/'.format(username)
+    #伪装header
+    headers = {
+        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0"
+    }
+    res = requests.get(url,headers)
+    if res.status_code == 200:
+        f = 0
+        text = res.content.decode('utf-8')
+        html = etree.HTML(text)
+        try:
+            rank = html.xpath("//div[@class='user-rank']/span[@class='user-legendary']/text()")[0]
+        except Exception as e:
+            sys.stderr.write("No such handle")
+            sys.exit(1)
+
+        try:
+            rating = html.xpath("//div[@class='info']/ul[1]/li[1]/span[1]/text()")[0]
+        except Exception as e:
+            #标记无rating记录
+            f = 1
+        if(f == 1):
+            res = {
+                "handle":username
+            }
+        else:
+            res ={
+                "handle":username,
+                "rating":rating,
+                "rank":rank[:-1] #去除最后一位空格
+            }
+        res_json = json.dumps(res)
+        sys.stdout.write(res_json)
+        sys.exit(0)
+    else:
+        sys.stderr.write("network anomaly")
+
+if __name__ == '__main__':
+    username = sys.argv[1:][0]
+    get_user_info(username)
+```
+
+## summary
+
+简单爬虫库的使用
+
+python的标准输入输出流
+
+json库的使用

works/huiduw/M1.2/cf_spider_api.py

@@ -0,0 +1,58 @@
+import requests
+import json
+import sys
+
+
+def get_user_info(username):
+    url = "https://codeforces.com/api/user.info"
+    headers = {
+        "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36 Edg/120.0.0.0"
+    }
+    # 配置参数
+    params = {
+        "handles": username
+    }
+    try:
+        res = requests.get(url,params, headers = headers)
+        info_json = res.json()
+        if info_json["status"] == "OK":
+            for user in info_json["result"]:
+                if "rank" not in user:
+                    user_info = {"handle": params["handles"]}
+                else:
+                    user_info = {
+                        "handle": params["handles"],
+                        "rating": user["rating"],
+                        "rank": user["rank"]
+                    }
+                user_json = json.dumps(user_info)
+                sys.stdout.write(user_json + "\n")
+        elif info_json["status"] == "FAILED":
+            sys.stderr.write("no such handle\n")
+            sys.exit(1)
+    except requests.exceptions.Timeout as e:
+        sys.stderr.write(f"请求超时: {e}\n")
+        sys.exit(1)
+    except requests.exceptions.HTTPError as e:
+        sys.stderr.write(f"HTTP错误: {e}\n")
+        sys.exit(1)
+    except requests.exceptions.ConnectionError as e:
+        sys.stderr.write(f"连接错误: {e}\n")
+        sys.exit(1)
+    except KeyError as e:
+        sys.stderr.write(f"API返回的数据不完整或不正确: {e}\n")
+        sys.exit(1)
+    except TypeError as e:
+        sys.stderr.write(f"返回的数据类型不正确: {e}\n")
+        sys.exit(1)
+
+def main():
+    try:
+        username = sys.argv[1:][0]
+        get_user_info(username)
+    except IndexError:
+        sys.stderr.write("用户名不能为空!\n")
+
+
+if __name__ == '__main__':
+    main()

works/huiduw/M2.1/cf_spider_back_V0.1.py

@@ -0,0 +1,89 @@
+from flask import Flask,request,jsonify
+import requests
+import json
+import sys
+app = Flask(__name__) #创建实例
+
+#错误信息
+ERROR_MESSAGES = {
+    "1": "no such handle",
+    "2": "No valid HTTP response was received",
+    "3": "Abnormal HTTP response",
+    "4": "Internal Server Error"
+}
+
+
+def get_user_info(username):
+    url = "https://codeforces.com/api/user.info"
+    # 配置参数
+    params = {
+        "handles": username
+    }
+
+    res = requests.get(url,params)
+    # print(res)
+    status = res.status_code
+    # print(status)
+    info_json = res.json()
+    # print(info_json)
+
+    if status == 200 or status == 400:
+        if info_json["status"] == "OK":
+            for user in info_json["result"]:
+                if "rank" not in user:
+                    user_info = {"handle": params["handles"]}
+                else:
+                    user_info = {
+                        "handle": params["handles"],
+                        "rating": user["rating"],
+                        "rank": user["rank"]
+                    }
+                user_json = json.dumps(user_info)
+                res_json = {
+                    "success": True,
+                    "result": user_json
+                }
+                return res_json
+        elif info_json["status"] == "FAILED":
+            res_json = {
+                "success": False,
+                "message": ERROR_MESSAGES['1']
+            }
+            return res_json
+    elif status == 404: #状态码404 未收到有效HTTP响应
+        res_json = {
+            "success": False,
+            "message": ERROR_MESSAGES['2']
+        }
+        return res_json
+    elif status // 100 == 4: #状态码4xx 异常HTTP响应
+        res_json = {
+            "success": False,
+            "message": ERROR_MESSAGES['3']
+        }
+        return res_json
+    elif status // 100 == 5: #状态码5xx 服务器错误
+        res_json = {
+            "success": False,
+            "message": ERROR_MESSAGES['4']
+        }
+        return res_json
+
+@app.route('/',methods =['GET'])
+def query():
+    data = []
+    try:
+        usernames = request.args.get('handles')
+        query_list = usernames.split(',')
+        for username in query_list:
+             result = get_user_info(username)
+             data.append(result)
+    except Exception as e:
+        return '传个参数先啦'
+
+    return jsonify(data)
+
+
+if __name__ == '__main__':
+    app.run('127.0.0.1',port=2333) #指定提供服务的端口号
+

works/huiduw/M2.1/record.md

@@ -0,0 +1,35 @@
+## Flask + http学习
+
+flask真是便便又利利呢
+
+## 总结
+
+**HTTP 协议的基本组成部分有**：请求行、请求头、请求体和响应行、响应头、响应体。
+
+请求行中包含方法、请求 URI 和 HTTP 版本。例如：GET /users/ahz HTTP/1.1。
+
+请求头中包含请求头名称和请求头参数。例如：Accept-Language: zh-CN,zh;q=0.9。
+
+请求体中包含请求数据。例如：{"username": "ahz", "password": "password"}。
+
+响应行中包含HTTP版本和状态码。例如：HTTP/1.1 200 OK。
+
+响应头中包含响应头名称和响应头参数。例如：Content-Type: application/json。
+
+响应体中包含响应数据。例如：{"success": True, "result": {"handle": "ahz"}}。
+
+**在 HTTP 请求中，常见的传参方式有：**
+
+1. Query Parameters：在 URL 的查询参数部分传递参数。例如：/users?handle=ahz。
+
+2. Body Parameters：将参数放在请求体中。例如：POST /users { "username": "ahz", "password": "password" }。
+
+3. Header Parameters：将参数作为请求头参数传递。例如：GET /users/ahz HTTP/1.1 Host: example.com。
+
+4. Path Parameters：将参数放在请求 URI 的路径部分。例如：GET /users/{handle}。
+
+## 优化方案
+
+1. 多线程
+2. 加缓存
+3. ~~想不到力~~