爬虫——爬虫Json.dumps保存多数据失败

最新推荐文章于 2024-01-11 10:58:15 发布

蒙牛没我牛:)

最新推荐文章于 2024-01-11 10:58:15 发布

阅读量495

点赞数

文章标签： json python

本文链接：https://blog.csdn.net/coke_l/article/details/128437576

版权

问题：我起初爬了豆瓣的一些数据下来，爬取了总共有10个界面，我代码里面的保存json文件代码是没问题的，但是一次只能保存一页，保存两页的话json文件就会变null（虽然保存失败但是控制台能够完全输出所有内容）求解

代码在这

import json
import time

from selenium import webdriver
import lxml.html
import requests
import uesragent

def parse_http_url(temp_url):       #抓取数据方法
    response = requests.get(temp_url,headers=uesragent.get_header())
    texts=response.content.decode("utf-8")
    return texts

def catch_moving_list(*group):     #抓取网页数据方法
    temp_text=group[0]
    count=group[1]
    if count !=0:
        all_moving_detail=group[2]
    else:
        all_moving_detail=[]
    html_source = temp_text
    metree = lxml.html.etree
    parser = metree.HTML(html_source)
    # xpath语法规范
    moving_li = parser.xpath("//ol[@class='grid_view']/li")
    # print(moving_list)
    for detail_moving in moving_li:
        moving_text= {}

        moving_name=detail_moving.xpath("./div/div[@class='pic']/a/img/@alt")[0]
        moving_text['电影名']=moving_name

        moving_src=detail_moving.xpath("./div/div[@class='pic']/a/@href")[0]
        moving_text['电影地址'] = moving_src

        moving_score = detail_moving.xpath("./div/div[@class='info']/div[@class='bd']/div/span[@class='rating_num']/text()")[0]
        moving_text['电影评分'] = moving_score

        moving_comment = detail_moving.xpath("./div/div[@class='info']/div[@class='bd']/div/span[last()]/text()")[0]
        moving_comment_len=len(moving_comment)
        moving_text['电影评价人数'] = moving_comment[0:moving_comment_len-3]
        count+=1

        all_moving_detail.append(moving_text)
        time.sleep(1)

    if count!=175:
        http_url = "https://movie.douban.com/top250?start="+str(count)+"&filter="
        text_html=parse_http_url(http_url)
        catch_moving_list(text_html,count,all_moving_detail)
    else:
        print(all_moving_detail)
        # print(count)
        return all_moving_detail

def save_all_moving_file(temp_text):  #保存文件方法
    moving_strs=json.dumps(temp_text,ensure_ascii=False,indent=3)
    # 打开文件
    moving_file=open('all_moving_datas.json','w',encoding='utf-8')
    # 写入数据
    moving_file.write(moving_strs)
    # 关闭文件
    moving_file.close()
    pass


def main():         #main方法，
    arr=[]
    num=125
    http_url="https://movie.douban.com/top250?start="+str(num)+"&filter="
    text_html=parse_http_url(http_url)
    more_moving_list=catch_moving_list(text_html,num,arr)
    save_all_moving_file(more_moving_list)
    pass

if __name__=='__main__':
    main();