commitFinish

TR/TrialRecommend/DataRequest.py

@@ -1,5 +1,7 @@
 import csv
 import random
+import urllib.parse
+
 from DrissionPage import ChromiumOptions
 from DrissionPage import ChromiumPage
 import time
@@ -24,9 +26,12 @@ class DataRequest:
         self.csv_writer=csv.DictWriter(self.f,fieldnames=['文章ID','文章标题','喜欢数量','图片资源'])
         #
         self.keyword=keyword
-        self.url='https://www.xiaohongshu.com/search_result?keyword='+self.keyword+'&type=51'
+
+        self.url=''
         #数据
         self.items=[]
+        #初始化URL编码
+        self.set_url()
         #打开浏览器
         self.drive=ChromiumPage()
         self.drive.set.scroll.smooth(on_off=True)
@@ -37,6 +42,13 @@ class DataRequest:
         self.drive.get(self.url)
         self.dataRequest()
 
+
+    def set_url(self):
+        self.url = ('https://www.xiaohongshu.com/search_result?keyword=' + self.url_encode(self.keyword))
+    def url_encode(self, s):
+        """将字符串转化为URL编码"""
+        return urllib.parse.quote(s, safe='')
+
     def clear_csv_file(self):
         with open(self.data_csv_file_path, 'w') as file1:  # 使用'w'模式打开文件
             pass  # 不需要执行任何操作，因为打开文件时内容已被清空

TR/TrialRecommend/Main.py

@@ -1,6 +1,7 @@
 import csv
 import os
 import random
+import shutil
 import tempfile
 import time
 import tkinter as tk
@@ -81,9 +82,9 @@ class Mainpage:
 
         self.btn_liked = tk.Button(self.page, text='收藏攻略', bg='#D7EFFF',font=('SimHei',15,'bold'),command=self.func_collect)
         self.btn_liked.place(relx=0.9, rely=0.2, relheight=0.05, relwidth=0.1)
-
-        self.btn_dis_liked = tk.Button(self.page, text='取消收藏', bg='#D7EFFF',font=('SimHei',15,'bold'),command=self.func_discollect)
-        self.btn_dis_liked.place(relx=0.9, rely=0.3, relheight=0.05, relwidth=0.1)
+        #
+        # self.btn_dis_liked = tk.Button(self.page, text='取消收藏', bg='#D7EFFF',font=('SimHei',15,'bold'),command=self.re)
+        # self.btn_dis_liked.place(relx=0.9, rely=0.3, relheight=0.05, relwidth=0.1)
 
         self.lable_like=tk.Label(self.page,text='喜欢人数:'+self.likes,font=('SimHei',15,'bold'))
         self.lable_like.place(relx=0.05, rely=0.93)
@@ -234,7 +235,7 @@ class Mainpage:
         self.btn_pre = tk.Button(self.page2, text='上一篇', bg='#D7EFFF',font=('SimHei',15,'bold'),command=self.c_pre_data)
         self.btn_pre.place(relx=0.45, rely=0.35, relheight=0.08, relwidth=0.09)
 
-        self.btn_dis_liked = tk.Button(self.page2, text='取消收藏', bg='#D7EFFF',font=('SimHei',15,'bold'),command=self.func_discollect)
+        self.btn_dis_liked = tk.Button(self.page2, text='取消收藏', bg='#D7EFFF',font=('SimHei',15,'bold'),command=self.remove_rows_with_content)
         self.btn_dis_liked.place(relx=0.9, rely=0.3, relheight=0.05, relwidth=0.1)
 
     def notes_request(self,next_back):
@@ -528,6 +529,7 @@ class Mainpage:
                 for row in reader:
                     if i==self.current_data_index:
                         dic['文章内容']=row[1]
+                    i+=1
 
             with open('collections/{}.csv'.format(self.user),'a+',encoding='utf-8',newline='') as f:
                 writer = csv.DictWriter(f, fieldnames=['文章ID','文章标题','图片资源','文章内容'])
@@ -560,7 +562,26 @@ class Mainpage:
         # 将临时文件重命名为原始文件名
         os.rename(temp.name, 'collections/{}.csv'.format(self.user))
 
+    def remove_rows_with_content(self):
+        dis_collect.dis_collec(self.user, self.c_data_index)
+
+        # 创建一个临时文件
+        with tempfile.NamedTemporaryFile(mode='w', delete=False,encoding='utf-8',newline='') as tmpfile:
+            # 打开原始文件并读取内容
+            with open('collections/{}.csv'.format(self.user), 'r', newline='',encoding='utf-8') as infile:
+                reader = csv.reader(infile)
+                writer = csv.writer(tmpfile)
+
+                # 遍历每一行，如果不包含指定内容则写入临时文件
+                i=0
+                for row in reader:
+                    if self.c_data_index != i:
+                        writer.writerow(row)
+                    i+=1
 
+                        # 替换原始文件为临时文件
+            tmpfile.close()
+            shutil.move(tmpfile.name, 'collections/{}.csv'.format(self.user))
 
 if __name__ == '__main__':
     root = tk.Tk()

TR/TrialRecommend/Notes_Request.py

@@ -15,15 +15,15 @@ def notes_request(url):
         'Referer':'https://www.xiaohongshu.com',
         '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'}
     cookies = {
-        'abRequestId':'a3c8a855-ed85-57f6-91fe-3e0acedffde8',
-        'a1':'18f9b67ecdbh41bri2la0dgguminrd7dmmrk4pxf750000215521',
-        'webId':'6d97ebd3e6051489537e7a6aa1d1cf99',
-        'gid':'yYijDKYydJ6JyYijDKWdS6UCfDx4yDF3J108FiWfkk763T28IFfWf4888Jy22Jy8WYf0SyjD',
-        'webBuild':'4.17.2',
-        'web_session':'040069b3643d32585fff79ee79344bd4b89bc6',
-        'acw_tc':'459a6388281f21d6215ff80f1402afbfdf47eb5a1ef949b426ace99565a6fc50',
-        'websectiga':'7750c37de43b7be9de8ed9ff8ea0e576519e8cd2157322eb972ecb429a7735d4',
-        'sec_poison_id':'b1e1329b-735f-427c-bfd0-698a912c0366',
+        'abRequestId':'a1d1855c-4c32-5307-a9f1-9d3f34a192cf',
+        'a1':'1900bc790f5y2g9t1mkcnviv0sy4y0pfv4afgtuj250000186611',
+        'webId':'b7d9160688e1684d896a4dc0dab65e36',
+        'gid':'yj88DSWfdJhjyj88DSWj8497i2vJkj9y6TSI0VJh3h8Mvi284v8Uik888yYKKyy8Wq48fY4i',
+        'webBuild':'4.20.1',
+        'web_session':'040069b3643d32585fffe2225c344b136354be',
+        'acw_tc':'5a6bd4ac6c786b806cb96212649c76bb7a0ac62792834403c50f508645293c50',
+        'websectiga':'3633fe24d49c7dd0eb923edc8205740f10fdb18b25d424d2a2322c6196d2a4ad',
+        'sec_poison_id':'b2862aa3-62f2-48ce-9b27-2a44baa4b714',
         'xsecappid':'xhs-pc-web'
 
     }

TR/TrialRecommend/TF_IDF.py

@@ -1,5 +1,4 @@
 import csv
-
 import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
@@ -7,16 +6,12 @@ from sklearn.metrics.pairwise import cosine_similarity
 def tf_idf(items, user):
     # 数据载入
     articles = items
-
     df = pd.DataFrame(articles)
-
     # 提取TF-IDF特征
     tfidf_vectorizer = TfidfVectorizer()
     tfidf_matrix = tfidf_vectorizer.fit_transform(df['content'])
-
     # 计算余弦相似度
     cosine_sim = cosine_similarity(tfidf_matrix, tfidf_matrix)
-
     # 根据相似度推荐
     def recommend_articles(article_id, user, cosine_sim=cosine_sim):
         sim_scores = list(enumerate(cosine_sim[article_id - 1]))
@@ -28,6 +23,5 @@ def tf_idf(items, user):
             for j in article_indices:
                 write.writerow(items[j])
 
-
     # 推荐与文章ID为1的旅游攻略相似的文章
     recommend_articles(1,user)

TR/TrialRecommend/collections/123.csv

@@ -0,0 +1 @@
+652e1987000000001a01728c,上海CityWalk丨花一天时间打卡经典路线‼️,"['http://sns-webpic-qc.xhscdn.com/202406121747/5d91eba5a30122575b2c4146228f05ae/1040g2sg30qamrg2c7m305o2pk3s08c1iul9cau0!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/acd054cac0306a40b3017b83b965aaae/1040g2sg30qamrg2c7m0g5o2pk3s08c1id68puj0!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/8a44ffaff123d9ac7cc8ce59804813cc/1040g2sg30qamrg2c7m105o2pk3s08c1irrp23qo!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/c838f8b3d6b4937fc9eb443eb9439a42/1040g2sg30qamrg2c7m005o2pk3s08c1ih4ij41g!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/a1091a8d90a659eb78aeeba1c27c11a0/1040g2sg30qamrg2c7m1g5o2pk3s08c1ierqbkeg!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/52484f0b10916edfec05be159b17b35c/1040g2sg30qamrg2c7m205o2pk3s08c1iinbrhl8!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/def3baa4ab87428dd9f7668c0e4a0d5b/1040g2sg30qamrg2c7m2g5o2pk3s08c1ivce38f8!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/720636b2cd678875f60aff8c59ac8bda/1040g2sg30qamrg2c7m3g5o2pk3s08c1i07b4gb0!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/422b9900a3da1949703eed0b17645597/1040g2sg30qamrg2c7m405o2pk3s08c1ira5no60!nc_n_webp_mw_1', 'http://sns-webpic-qc.xhscdn.com/202406121747/b7fb32de5dc7ef70ac09d95884107cd7/1040g2sg30qamrg2c7m4g5o2pk3s08c1iuenb4no!nc_n_webp_mw_1']",上海总要来一趟吧<br/>确实好拍又好逛<br/>如果你只有周末有时间<br/>可以看看我总结的这篇一日游攻略<br/>主打一个花zui少的时间<br/>逛完zui经典的上海<br/>.<br/>✅CityWalk路线<br/>武康大楼—武康路/长乐路—静安寺—陆家嘴三件套—轮渡—外滩(白天)—豫园/城隍庙—南京路步行街—外滩(夜景)<br/>.<br/>1️⃣武康大楼<br/>🚈地铁10、11号线交通大学站7号口出<br/>作为上海地标建筑之一，超火的网红打卡点，始建于1924年，中国历史文化名街，附近有【宋庆龄故居】选择性游玩（🎫20r）<br/>.<br/>2️⃣武康路/长乐路<br/>比较有上海当地人文气息的宝藏徒步路线，一路可以逛吃不停，街边都是梧桐树，秋天的梧桐树不用我说了吧！氛围感拉满，还有好多爆火的网红店都在这条路线上<br/>.<br/>3️⃣静安寺<br/>作为上海zui古老的寺庙，琉璃金瓦的古塔建筑被现代化建筑包围，碰撞出了别致的美感<br/>🎫50，如果不是特意要去拜佛可以不去，zui佳打卡机位在对面人行天桥上，（如果到饭点了，可以在静安寺站这附近吃，楼下有商场）<br/>.<br/>4️⃣陆家嘴三件套<br/>📍导航【金茂君悦大酒店】，地铁静安寺站乘至陆家嘴站8号口出<br/>📷zui佳拍摄机位需要站在花坛边缘，zui容易拍的方式是手机打开广角，手机就放在脚下，摆好动作定时拍摄<br/>.<br/>5️⃣轮渡—外滩（白天）<br/>🛥2块钱看尽黄浦江两岸风景<br/>打卡完三件套，步行至【东昌路渡口】，乘坐轮渡到【金陵东路渡口】，2块钱坐上轮渡，到了外滩就是上海zui核心的地标了，这里有万国建筑群，对面就是东方明珠群像<br/>.<br/>6️⃣豫园/城隍庙（选择性游玩）<br/>豫园🎫30r/城隍庙10r（商业街免费）<br/>豫园是拥有四百多年历史的江南园林，纸醉金迷上海滩的一处世外桃源，一草一木都不输苏州园林，城隍庙就在豫园隔壁，蛮好逛的<br/>.<br/>7️⃣南京路步行街<br/>上海zui具代表性的商业街区，非常适合逛吃，东方明珠的打卡机位也穿插在各个街道<br/>.<br/>8️⃣外滩（夜景）<br/>来上海怎么能不看外滩夜景呢！金黄色的万国建筑群和对岸东方明珠建筑群无不展示了现代都市美<br/>.<br/>📍交通<br/>🚈高铁杭州东-上海虹桥站<br/>✅游玩路线以地铁+步行为主<br/>地铁可以刷zfb或者下载Metro大都会app<br/>.<br/>

TR/abc.py

@@ -0,0 +1,12 @@
+import urllib.parse
+
+
+def url_encode(s):
+    """将字符串转化为URL编码"""
+    return urllib.parse.quote(s, safe='')
+
+
+# 示例
+input_string = input("请输入要编码的字符串：")
+encoded_string = url_encode(input_string)
+print(encoded_string)