爬虫结束自动打标注

This commit is contained in:
juanboy
2024-07-04 15:46:28 +08:00
parent 52bc0028aa
commit 406939eaaa
+3 -5
View File
@@ -69,13 +69,11 @@ def getTopicCreatedAtandpredictData(topic):# 统计特定话题的评论在每
else: else:
createdAt[i[1]] = 1 createdAt[i[1]] = 1
createdAt = {k: createdAt[k] for k in sorted(createdAt, key=lambda date: datetime.datetime.strptime(date, "%Y-%m-%d"))} createdAt = {k: createdAt[k] for k in sorted(createdAt, key=lambda date: datetime.datetime.strptime(date, "%Y-%m-%d"))}
print(createdAt)
createdAt.update(predict_future_values(createdAt)) createdAt.update(predict_future_values(createdAt))
print(createdAt)
sorted_data = {k: createdAt[k] for k in sorted(createdAt, key=lambda date: datetime.datetime.strptime(date, "%Y-%m-%d"))} sorted_data = {k: createdAt[k] for k in sorted(createdAt, key=lambda date: datetime.datetime.strptime(date, "%Y-%m-%d"))}
return topic,sorted_data result_list = [0] * (len(sorted_data) - 5) + [1] * 5
# return topic,list(createdAt.keys()),list(createdAt.values()) return topic,sorted_data,result_list
# return topic, createdAt.items() # return topic,list(createdAt.keys()),list(createdAt.values()),result_list
def writeTopicsToCSV(topics, file_name): def writeTopicsToCSV(topics, file_name):
# 检查文件是否存在,如果存在则附加写入,否则新建一个 # 检查文件是否存在,如果存在则附加写入,否则新建一个