新增了实体类，对于两个up及以上的视频，把粉丝数设置为1

controller/SpyderController.py

@@ -6,6 +6,8 @@ import json
 import requests
 from lxml import etree
 
+from entity.BilibiliVideo import BilibiliVideo
+
 
 class SpyderController:
     # Bilibili视频爬虫控制器,打开网页，爬取BilibiliVideo.py中的数据,将其下载下来，保存为csv文件
@@ -17,6 +19,10 @@ class SpyderController:
         :param waitTime:float: 每个线程的等待时间，单位秒（避免爬取过快）
         :return: list[BilibiliVideo] 返回处理完成后的videoList
         """
+        all_data_list = []
+        videoCount = int(videoCount)
+        threadCount = int(threadCount)
+        waitTime = float(waitTime)
         if videoCount < threadCount:
             threadCount = videoCount
         if videoCount > 20:
@@ -76,11 +82,14 @@ class SpyderController:
                 bulletCount = convert_to_number(bulletCount)
                 # match = re.search(r'\d+', text)
                 # number = match.group()
-                followers_str = creatorFanCount[0].strip().split()[1]
-                followers_num = float(followers_str.replace('万', '')) * 10000
-                # 转化为整数
-                followers_num = int(followers_num)
-                creatorFanCount = [str(followers_num)]
+                if not creatorFanCount:
+                    creatorFanCount = [str(1)]
+                else :
+                    followers_str = creatorFanCount[0].strip().split()[1]
+                    followers_num = float(followers_str.replace('万', '')) * 10000
+                    # 转化为整数
+                    followers_num = int(followers_num)
+                    creatorFanCount = [str(followers_num)]
                 commentCount = [str(parsed_data['data']['list'][i]['stat']['reply'])]
                 creatorId = [str(parsed_data['data']['list'][i]['owner']['mid'])]
                 creatorName = [str(parsed_data['data']['list'][i]['owner']['name'])]
@@ -91,13 +100,16 @@ class SpyderController:
                 up_text = requests.get(url=up_url, headers=headers).text
                 tree = etree.HTML(up_text)
                 #print(up_text)
+                all_data = bvId + title + [url] + uploadTime + topNo + viewCount + likeCount + coinCount + favoriteCount + bulletCount + commentCount + creatorId + creatorName + creatorFanCount
 
-                all_data = topNo + bvId + title + [
-                    video_url] + uploadTime + viewCount + likeCount + coinCount + favoriteCount + bulletCount + commentCount + creatorId + creatorName + creatorFanCount
                 csv_writer.writerow(all_data)
-                all_data_list = []
-                all_data_list = all_data_list + [topNo, bvId, title, [video_url], uploadTime, viewCount, likeCount, coinCount, favoriteCount, bulletCount, commentCount, creatorId, creatorName, creatorFanCount]
+
+                # all_data_list = all_data_list + [topNo, bvId, title, [video_url], uploadTime, viewCount, likeCount, coinCount, favoriteCount, bulletCount, commentCount, creatorId, creatorName, creatorFanCount]
+                video = BilibiliVideo(bvId[0], title[0], url, int(uploadTime[0]), int(topNo[0]), int(viewCount[0]), int(likeCount[0]), int(coinCount[0]),
+                 int(favoriteCount[0]), int(commentCount[0]), int(bulletCount[0]), creatorId[0], creatorName[0], int(creatorFanCount[0]))
+                all_data_list.append(video)
             f.close()
+            # print(all_data_list)
             return all_data_list
 
         thread_list = []
@@ -113,15 +125,15 @@ class SpyderController:
 
         for thread in thread_list:
             thread.join()
-
+        print(all_data_list)
+        return all_data_list
 
 if __name__ == '__main__':
     f = open("file_3.csv", "w", encoding="UTF-8", newline="")
     csv_writer = csv.writer(f)
     csv_writer.writerow(
-        ["topNo", "bvId", "title", "url", "uploadTime", "viewCount", "likeCount", "coinCount", "favoriteCount",
-         "bulletCount", "commentCount",
-         "creatorId", "creatorName", "creatorFanCount"])
+        ["bvId", "title", "url", "uploadTime", "topNo", "viewCount", "likeCount", "coinCount",
+                 "favoriteCount", "commentCount", "bulletCount", "creatorId", "creatorName", "creatorFanCount"])
     f.close()
     spyderController = SpyderController()
     spyderController.getBilibiliVideoList(6, 2, 0.3)  # 设置线程数为2

controller/UIController.py

@@ -39,9 +39,10 @@ class UIController:
             waitTime=entry3.get()
             #创建 SpyderController对象调用其函数
             SpyderController=SC.SpyderController()
-            global scRuslt_data
-            scRuslt_data=SpyderController.getBilibiliVideoList(videoCount,threadCount,waitTime)
+            # global scRuslt_data
+            self.scRuslt_data=SpyderController.getBilibiliVideoList(videoCount,threadCount,waitTime)
             print("爬取完成")
+            # print(scRuslt_data)
 
 
 

service/CsvService.py

@@ -17,5 +17,5 @@ class CsvService(IFileService):
                  video.coinCount, video.favoriteCount, video.bulletCount, video.commentCount,
                  video.creatorId, video.creatorName, video.creatorFanCount])
         f.close()
-        raise NotImplementedError
+        # raise NotImplementedError