juanboy

爬虫结束自动打标注

@@ -39,7 +39,7 @@ def topicdefine(): @@ -39,7 +39,7 @@ def topicdefine():
39 for x in articleList: 39 for x in articleList:
40 label_article.append((x[0],predict_topic(x[5]))) 40 label_article.append((x[0],predict_topic(x[5])))
41 for x in commentList: 41 for x in commentList:
42 - label_comments.append((x[8],predict_topic(x[4]))) 42 + label_comments.append((x[5],x[8],predict_topic(x[4])))
43 return label_article,label_comments 43 return label_article,label_comments
44 44
45 # 更新数据库 45 # 更新数据库
@@ -53,14 +53,14 @@ def update_data(): @@ -53,14 +53,14 @@ def update_data():
53 params = [str(label),str(id)] 53 params = [str(label),str(id)]
54 query(sql, params) 54 query(sql, params)
55 for row in label_comments: 55 for row in label_comments:
56 - id, label = row  
57 - sql = "UPDATE comments SET label = %s WHERE authorName = %s"  
58 - params = [str(label),str(id)] 56 + id,image,label = row
  57 + sql = "UPDATE comments SET label = %s WHERE authorName=%s AND authorAvatar = %s"
  58 + params = [str(label),str(id),str(image)]
59 query(sql, params) 59 query(sql, params)
60 60
61 61
62 if __name__ == '__main__': 62 if __name__ == '__main__':
  63 + # drop_label()
  64 + # drop_label1()
63 update_data() 65 update_data()
64 #删除文章和评论的标签列 66 #删除文章和评论的标签列
65 -# drop_label()  
66 -# drop_label1()