利用pyhton整理生活中的小事情

一, 需求说明

1.我想要保存喜欢的up公开的相薄的所有图片和下方配文
2. 我想要记录一下每条动态的发布时间
3. 我想要每个动态保存到一个以发布日期命名的文件夹下，方便回忆
4. 我想要每个动态的下方配文保存成一个txt文档，方便我查看和保存

二，技术选型： python

三, 分析与代码实现:

经分析发现：

1.存在一个接口我们可以查看up主的相薄总条数

例如其中一个人的uid为: 9824766
访问接口:
https://api.bilibili.com/x/dynamic/feed/draw/upload_count?uid=9824766&jsonp=jsonp
浏览器得到的响应为：

uid = input("请输入up主的uid,然后按回车键: ")
# 得到总的相薄中动态的总个数
uid_url = 'https://api.bilibili.com/x/dynamic/feed/draw/upload_count?uid=' + uid + '&jsonp=jsonp'
header = {'user-agent': 'Mozilla/5.0'}
count_request = requests.get(uid_url, headers=header)
count_res = json.loads(count_request._content)
count = count_res.get('data').get('all_count')
print("相薄里的动态个数为: "+count)

2.存在一个接口，可以根据传的页数参数返回一个带有description,img_src数组 和ctime 发布时间 json响应

接口格式如下:
https://api.bilibili.com/x/dynamic/feed/draw/doc_list?uid=’ + uid + ‘&page_num=’ + str(page_num) + ‘&page_size=30&biz=all&jsonp=jsonp’
例如访问某up的第一页相薄：
https://api.bilibili.com/x/dynamic/feed/draw/doc_list?uid=9824766&page_num=0&page_size=30&biz=all&jsonp=jsonp

解析代码:

def getRecords(url):
    r = requests.get(url, headers=header)
    status = r.status_code
    if (200 == status):
        contentDir = json.loads(r._content)
        items = contentDir.get('data').get('items')
        Records = []
        for item in items:
            oneRecord = {}
            description = item.get('description')
            pictures = item.get('pictures')
            timeStamp = item.get('ctime')
            timearr = time.localtime(timeStamp)
            ctime = time.strftime("%Y_%m_%d_%H_%M_%S", timearr)
            srcList = []
            picture_size = len(pictures)
            for picture in pictures:
                src = picture.get('img_src')
                srcList.append(src)
            oneRecord.setdefault('desc', description)
            oneRecord.setdefault('src', srcList)
            oneRecord.setdefault('ctime', ctime)
            Records.append(oneRecord)
    return Records

3.访问每一页

通过1,2我们可以查看到一个up主相薄里动态的总个数，也知道一页是30个，
那么我们就能知道有多少页，拼接页数参数就能去访问每一页了

uid = input("请输入up主的uid,然后按回车键: ")
page_num = 0
while count > 0:
    url = 'https://api.bilibili.com/x/dynamic/feed/draw/doc_list?uid=' + uid + '&page_num=' + str(page_num) + '&page_size=30&biz=all&jsonp=jsonp'
    #得到一页中的的description和img_src 和ctime
    records = getRecords(url)
    print("第 "+str(page_num)+'页 开始在下载')
 	# 下载 1页中的相薄和description
    download(records)
    page_num += 1
    count = count - 30

4.图片下载和description写为txt，文件夹名字为发布时间ctime

def download(records):
    for record in records:
        ctime = record.get('ctime')
        dir = os.getcwd() + "\\image\\" + ctime + "\\"
        if not os.path.exists(dir):
            os.makedirs(dir)
        urls = record.get('src')
        description = record.get('desc')
        for url in urls:
            r = requests.get(url)
            file_path = os.path.splitext(url)[0]
            file_name = file_path.split('/')[-1]
            with open(dir + file_name + '.jpg', 'wb') as f:
                f.write(r.content)
        # 写文本文件
        with open(dir + '/description.txt', encoding='utf-8', mode='w') as f:
            f.write(str(description))

四，全部代码整理

# coding:utf-8
import os
import requests
import json
import time
def download(records):
    for record in records:
        ctime = record.get('ctime')
        dir = os.getcwd() + "\\image\\" + ctime + "\\"
        if not os.path.exists(dir):
            os.makedirs(dir)
        urls = record.get('src')
        description = record.get('desc')
        for url in urls:
            r = requests.get(url)
            file_path = os.path.splitext(url)[0]
            file_name = file_path.split('/')[-1]
            with open(dir + file_name + '.jpg', 'wb') as f:
                f.write(r.content)
        # 写文本文件
        with open(dir + '/description.txt', encoding='utf-8', mode='w') as f:
            f.write(str(description))

def getRecords(url):
    r = requests.get(url, headers=header)
    status = r.status_code
    if (200 == status):
        contentDir = json.loads(r._content)
        items = contentDir.get('data').get('items')
        Records = []
        for item in items:
            oneRecord = {}
            description = item.get('description')
            pictures = item.get('pictures')
            timeStamp = item.get('ctime')
            timearr = time.localtime(timeStamp)
            ctime = time.strftime("%Y_%m_%d_%H_%M_%S", timearr)
            srcList = []
            picture_size = len(pictures)
            for picture in pictures:
                src = picture.get('img_src')
                srcList.append(src)
            oneRecord.setdefault('desc', description)
            oneRecord.setdefault('src', srcList)
            oneRecord.setdefault('ctime', ctime)
            Records.append(oneRecord)
    return Records


# uid = '546195'
uid = input("请输入up主的uid,然后按回车键: ")
# 得到总的相薄中动态的总个数
uid_url = 'https://api.bilibili.com/x/dynamic/feed/draw/upload_count?uid=' + uid + '&jsonp=jsonp'
header = {'user-agent': 'Mozilla/5.0'}
count_request = requests.get(uid_url, headers=header)
count_res = json.loads(count_request._content)
count = count_res.get('data').get('all_count')

# 第几页
page_num = 0
while count > 0:
    url = 'https://api.bilibili.com/x/dynamic/feed/draw/doc_list?uid=' + uid + '&page_num=' + str(page_num) + '&page_size=30&biz=all&jsonp=jsonp'
    records = getRecords(url)
    print("第 "+str(page_num)+' 正在下载')
    download(records)
    page_num += 1
    count = count - 30

五,效果

github链接