Python基于pandas实现json格式转换成dataframe的方法

Python基于基于pandas实现实现json格式转换成格式转换成dataframe的方法的方法

主要介绍了Python基于pandas实现json格式转换成dataframe的方法,结合实例形式分析了Python使用pandas模

块操作json数据转换成dataframe的相关操作技巧与注意事项,需要的朋友可以参考下

本文实例讲述了Python基于pandas实现json格式转换成dataframe的方法。分享给大家供大家参考，具体如下：

# -*- coding:utf-8 -*-

#!python3

import re

import json

def __init__(self):

self.picture_url = {

"image_id": '',

"picture_url": ''

}

class data_structs():

def __init__(self):

# columns=['title', 'item_url', 'id','picture_url','std_desc','description','information','fitment'])

self.info={

"title":'',

"fitment":''

}

# "https://waldoch.com/store/catalogsearch/result/index/?cat=0&limit=200&p=1&q=nerf+bar"

# https://waldoch.com/store/new-oem-ford-f-150-f150-5-running-boards-nerf-bar-crew-cab-2015-w-brackets-fl34-16451-ge5fm6.html

def get_item_list(outfile):

result = []

for i in range(6):

print(i)

i = str(i+1)

url = "https://waldoch.com/store/catalogsearch/result/index/?cat=0&limit=200&p="+i+"&q=nerf+bar"

result.append([title,item_url])

df = pd.DataFrame(result,columns=["title","item_url"])

df = df.drop_duplicates()

df["id"] =df.index

df.to_excel(outfile,index=False)

def get_item_info(file,outfile):

DEFAULT_FALSE = ""

df = pd.read_excel(file)

for i in df.index:

id = df.loc[i,"id"]

# 图片

imglink = soup.find_all("img", class_=re.compile("^gallery-image"))

data = data_structs()

data.info["title"] = df.loc[i,"title"]

data.info["id"] = id

data.info["item_url"] = item_url

for a in imglink:

image = image_structs()

image.picture_url["image_id"] = a["id"]

image.picture_url["picture_url"]=a["src"]