Github
/
examples-of-web-crawlers
mirror of
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

修复pa.per接口出错问题

This commit is contained in:
sqzhang 2022-03-18 21:52:29 +08:00
parent eb39dd76ad
commit 5b986829fe
5 changed files with 178 additions and 154 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

50
5.爬取5K分辨率超清唯美壁纸/README.MD
View File

@ -6,17 +6,34 @@
<br />
<br />
这里有一款Mac下的小清新壁纸神器[Pap.er][3]，可能是Mac下最好的壁纸软件，**自带5K超清分辨率壁纸**，富有多种类型壁纸，当我们想在Windows或者Linux下使用的时候，就可以考虑将**5K超清分辨率壁纸**爬取下来。
## 功能截图
![](example1.png)
![](example2.gif)
## 如何运行
```bash
# 跳转到当前目录
cd 目录名
# 先卸载依赖库
pip uninstall -y -r requirement.txt
# 再重新安装依赖库
pip install -r requirement.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
# 开始运行
python main.py
```
## 编写思路
首先，打开Charles软件，进行抓包。打开[Pap.er][3]，开始抓包。(由于是Mac系统下的APP，所以非Mac系统的朋友可以直接看抓包结果)
抓包分析结果如下：
首先，打开Charles软件，进行抓包。打开[Pap.er][3]，开始抓包。抓包分析结果如下：
| 类型 | 地址 |
| ---- | ------------------------------------------------------------ |
@ -141,27 +158,6 @@ if __name__ == '__main__':
## 使用教程
1. 确保以下库均已安装：
```python
# 如果没有安装，请使用pip install module安装
import requests
import filetype
import os
import json
from contextlib import closing
```
## 演示图片
![](example1.png)
![](example2.gif)
## 完整源代码
项目源代码在[GitHub仓库][1]
@ -170,7 +166,7 @@ from contextlib import closing
# License
## License
[The MIT License (MIT)][2]

113
5.爬取5K分辨率超清唯美壁纸/crawler_5K_wallpaper.py
View File

@ -1,113 +0,0 @@
# -*- coding:utf-8 -*-
from requests import get
from filetype import guess
from os import rename
from os import makedirs
from os.path import exists
from json import loads
from contextlib import closing
# 文件下载器
def Down_load(file_url, file_full_name, now_photo_count, all_photo_count):
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
# 开始下载图片
with closing(get(file_url, headers=headers, stream=True)) as response:
chunk_size = 1024 # 单次请求最大值
content_size = int(response.headers['content-length']) # 文件总大小
data_count = 0 # 当前已传输的大小
with open(file_full_name, "wb") as file:
for data in response.iter_content(chunk_size=chunk_size):
file.write(data)
done_block = int((data_count / content_size) * 50)
data_count = data_count + len(data)
now_jd = (data_count / content_size) * 100
print("\r %s：[%s%s] %d%% %d/%d" % (file_full_name, done_block * '█', ' ' * (50 - 1 - done_block), now_jd, now_photo_count, all_photo_count), end=" ")
# 下载完图片后获取图片扩展名，并为其增加扩展名
file_type = guess(file_full_name)
rename(file_full_name, file_full_name + '.' + file_type.extension)
# 爬取不同类型图片
def crawler_photo(type_id, photo_count):
# 最新 1, 最热 2, 女生 3, 星空 4
if(type_id == 1):
url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c68ffb9463b7fbfe72b0db0?page=1&per_page=' + str(photo_count)
elif(type_id == 2):
url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c69251c9b1c011c41bb97be?page=1&per_page=' + str(photo_count)
elif(type_id == 3):
url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c81087e6aee28c541eefc26?page=1&per_page=' + str(photo_count)
elif(type_id == 4):
url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/5c81f64c96fad8fe211f5367?page=1&per_page=' + str(photo_count)
# 获取图片列表数据
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
respond = get(url, headers=headers)
photo_data = loads(respond.content)
# 已经下载的图片张数
now_photo_count = 1
# 所有图片张数
all_photo_count = len(photo_data)
# 开始下载并保存5K分辨率壁纸
for photo in photo_data:
# 创建一个文件夹存放我们下载的图片
if not exists('./' + str(type_id)):
makedirs('./' + str(type_id))
# 准备下载的图片链接
file_url = photo['urls']['raw']
# 准备下载的图片名称,不包含扩展名
file_name_only = file_url.split('/')
file_name_only = file_name_only[len(file_name_only) -1]
# 准备保存到本地的完整路径
file_full_name = './' + str(type_id) + '/' + file_name_only
# 开始下载图片
Down_load(file_url, file_full_name, now_photo_count, all_photo_count)
now_photo_count = now_photo_count + 1
if __name__ == '__main__':
# 最新 1, 最热 2, 女生 3, 星空 4
# 爬取类型为3的图片(女生),一共准备爬取20000张
wall_paper_id = 1
wall_paper_count = 10
while(True):
# 换行符
print('\n\n')
# 选择壁纸类型
wall_paper_id = input("壁纸类型：最新壁纸 1, 最热壁纸 2, 女生壁纸 3, 星空壁纸 4\n请输入编号以便选择5K超清壁纸类型：")
# 判断输入是否正确
while(wall_paper_id != str(1) and wall_paper_id != str(2) and wall_paper_id != str(3) and wall_paper_id != str(4)):
wall_paper_id = input("壁纸类型：最新壁纸 1, 最热壁纸 2, 女生壁纸 3, 星空壁纸 4\n请输入编号以便选择5K超清壁纸类型：")
# 选择要下载的壁纸数量
wall_paper_count = input("请输入要下载的5K超清壁纸的数量：")
# 判断输入是否正确
while(int(wall_paper_count) <= 0):
wall_paper_count = input("请输入要下载的5K超清壁纸的数量：")
# 开始爬取5K高清壁纸
print("正在下载5K超清壁纸，请稍等……")
crawler_photo(int(wall_paper_id), int(wall_paper_count))
print('\n下载5K高清壁纸成功!')

138
5.爬取5K分辨率超清唯美壁纸/main.py Normal file
View File

@ -0,0 +1,138 @@
# -*- coding:utf-8 -*-
import requests
from filetype import guess
from os import rename
from os import makedirs
from os.path import exists
import json
from contextlib import closing
headers = {"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
def get_photo_type():
"""
获取可以爬取的壁纸类型
:return:
"""
url = "https://service.paper.meiyuan.in/api/v2/columns"
res = requests.get(url=url, headers=headers, verify=False)
res_json = json.loads(res.text)
return res_json
def down_load(file_url, file_full_name, now_photo_count, all_photo_count):
"""
文件下载器
:param file_url:
:param file_full_name:
:param now_photo_count:
:param all_photo_count:
:return:
"""
# 开始下载图片
with closing(requests.get(file_url, headers=headers, stream=True)) as response:
chunk_size = 1024 # 单次请求最大值
content_size = int(response.headers['content-length']) # 文件总大小
data_count = 0 # 当前已传输的大小
with open(file_full_name, "wb") as file:
for data in response.iter_content(chunk_size=chunk_size):
file.write(data)
done_block = int((data_count / content_size) * 50)
data_count = data_count + len(data)
now_jd = (data_count / content_size) * 100
print("\r %s：[%s%s] %d%% %d/%d" % (file_full_name, done_block * '█', ' ' * (50 - 1 - done_block), now_jd, now_photo_count, all_photo_count), end=" ")
# 下载完图片后获取图片扩展名，并为其增加扩展名
file_type = guess(file_full_name)
rename(file_full_name, file_full_name + '.' + file_type.extension)
def crawler_photo(type_id, photo_count):
"""
爬取不同类型图片
:param type_id:
:param photo_count:
:return:
"""
url = 'https://service.paper.meiyuan.in/api/v2/columns/flow/{}?page=1&per_page={}'.format(type_id, photo_count)
# 获取图片列表数据
respond = requests.get(url, headers=headers, verify=False)
photo_data = json.loads(respond.content)
# 已经下载的图片张数
now_photo_count = 1
# 所有图片张数
all_photo_count = len(photo_data)
# 开始下载并保存5K分辨率壁纸
for photo in photo_data:
# 创建一个文件夹存放下载的图片
if not exists('./' + str(type_id)):
makedirs('./' + str(type_id))
# 准备下载的图片链接
file_url = photo['urls']['raw']
# 准备下载的图片名称,不包含扩展名
file_name_only = file_url.split('/')
file_name_only = file_name_only[len(file_name_only) - 1]
# 准备保存到本地的完整路径
file_full_name = './' + str(type_id) + '/' + file_name_only
# 开始下载图片
down_load(file_url, file_full_name, now_photo_count, all_photo_count)
now_photo_count = now_photo_count + 1
if __name__ == '__main__':
# 获取可以爬取的壁纸类型
res_json = get_photo_type()
# 壁纸类型
wall_paper_id = 0
# 壁纸数量
wall_paper_count = 10
info_str = "壁纸类型："
for index, p_type in enumerate(res_json):
info_str = info_str + "{} {}".format(index, p_type['langs']['zh-Hans-CN'])
if index != len(res_json) - 1:
info_str = info_str + ", "
# 选择壁纸类型，并判断输入是否正确
while True:
wall_paper_id = input(info_str + "\n请输入编号以便选择5K超清壁纸类型：")
wall_paper_id = wall_paper_id.strip()
wall_paper_id = int(wall_paper_id)
if wall_paper_id >= len(res_json) or wall_paper_id < 0:
continue
else:
break
# 选择壁纸数量，并判断输入是否正确
while True:
wall_paper_count = input("请输入要下载的5K超清壁纸的数量：")
wall_paper_count = wall_paper_count.strip()
wall_paper_count = int(wall_paper_count)
if wall_paper_count <= 0:
continue
else:
break
# 开始爬取5K高清壁纸
print("正在下载5K超清壁纸，请稍等……")
crawler_photo(res_json[wall_paper_id]['_id'], wall_paper_count)
print('\n下载5K高清壁纸完毕，壁纸位于当前的{}目录。'.format(res_json[wall_paper_id]['_id']))

2
5.爬取5K分辨率超清唯美壁纸/requirement.txt Normal file
View File

@ -0,0 +1,2 @@
requests
filetype

29
README.MD
View File

@ -190,25 +190,26 @@ weibo_password = "改成你的微博密码"
这里有一款Mac下的小清新壁纸神器[Pap.er][8]，可能是Mac下最好的壁纸软件，**自带5K超清分辨率壁纸**，富有多种类型壁纸，当我们想在Windows或者Linux下使用的时候，就可以考虑将**5K超清分辨率壁纸**爬取下来。
### 使用教程
1. 确保以下库均已安装：
```python
# 如果没有安装，请使用pip install module安装
import requests
import filetype
import os
import json
from contextlib import closing
```
### 演示图片
### 功能截图
![](5.爬取5K分辨率超清唯美壁纸/example1.png)
![](5.爬取5K分辨率超清唯美壁纸/example2.gif)
### 如何运行
```bash
# 跳转到当前目录
cd 目录名
# 先卸载依赖库
pip uninstall -y -r requirement.txt
# 再重新安装依赖库
pip install -r requirement.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
# 开始运行
python main.py
```