我准备爬取https://m.lread.net的一本小说,这小说有时候 一个章节分了两页html。我如何将第二页的内容与前一页内容合并,保存到csv文件里?
#pipelines.py import csv class RuanyunPipeline(object): def __init__(self): self.filename= open('douluodalu.csv','w',newline="",encoding='utf-8') self.writer=csv.writer(self.filename) self.writer.writerow(['title','url_next','content']) def process_item(self, item, spider): if '-' not in item['url_now']: self.writer.writerow([item['title'],item['url_now'],item['content']]) else : self.writer.writerow([item['title'],item['url_now'],item['content']]) return item def close_spider(self,spider): if self.filename: self.filename.close()