python爬取精美壁纸图片（阴阳师）

一、requests获取数据

import requests

if not os.path.exists('02-heng'):
    os.makedirs('02-heng')

url = "https://yys.163.com/media/picture.html"
headers = {
            "User-Agent": "Mozilla/5.0(Windows NT 6.1;WOW64) AppleWebKit/537.36(KABUL, like Gecko) "
                            "Chrome/86.0.4240.198Safari/537.36 "
        }
resp = requests.get(url=url, headers=headers)
# print(resp.text)
# resp.encoding = resp.apparent_encoding

二、xpath解析数据，得到想要的图片连接

from lxml import etree

e = etree.HTML(resp.text)
images_heng = e.xpath("//div[@class='tab-cont'][1]/div/div/div/a/@href")
# print(images_heng)
# for i in images_heng:
#     print(i)
lst_1 = []
for url in images_heng:
    # print(url)
    imges_1 =url.split('/')
    if imges_1[-1][:-4] == "2732x2048":
        lst_1.append(url)
    # print(lst_1)
    # break
 

三、with open('**.jpg','wb')存储数据

for url in lst_1:
    time.sleep(1)
    resp = requests.get(url, headers=headers)
    file_name = url[url.rindex('picture'):url.rindex('/')].replace('/', '_')+ '.jpg'
    # print(file_name)
    print("正在保存："+ file_name+ "壁纸")
    with open(f'02-heng/{file_name}', 'wb') as f:
        f.write(resp.content)

print("全部保存完毕")

四、其它注意事项。爬取速度、保存目录的建立

import os
import time
if not os.path.exists('02-heng'):
    os.makedirs('02-heng')

分辨率为2732X2048高清晰图片（横版）：

import requests
from lxml import etree
import os
import time


if not os.path.exists('02-heng'):
    os.makedirs('02-heng')

url = "https://yys.163.com/media/picture.html"
headers = {
            "User-Agent": "Mozilla/5.0(Windows NT 6.1;WOW64) AppleWebKit/537.36(KABUL, like Gecko) "
                            "Chrome/86.0.4240.198Safari/537.36 "
        }
resp = requests.get(url=url, headers=headers)
# print(resp.text)
# resp.encoding = resp.apparent_encoding
# with open('a.txt', 'w') as f:
#     f.write(resp.text)
e = etree.HTML(resp.text)
images_heng = e.xpath("//div[@class='tab-cont'][1]/div/div/div/a/@href")
# print(images_heng)
# for i in images_heng:
#     print(i)
lst_1 = []
for url in images_heng:
    # print(url)
    imges_1 =url.split('/')
    if imges_1[-1][:-4] == "2732x2048":
        lst_1.append(url)
    # print(lst_1)
    # break
for url in lst_1:
    time.sleep(1)
    resp = requests.get(url, headers=headers)
    file_name = url[url.rindex('picture'):url.rindex('/')].replace('/', '_')+ '.jpg'
    # print(file_name)
    print("正在保存："+ file_name+ "壁纸")
    with open(f'02-heng/{file_name}', 'wb') as f:
        f.write(resp.content)

print("全部保存完毕")

分辨率为1080X1920高清晰图片（竖版）：

import requests
from lxml import etree
import os
import time


if not os.path.exists('02-shu'):
    os.makedirs('02-shu')

url = "https://yys.163.com/media/picture.html"
headers = {
            "User-Agent": "Mozilla/5.0(Windows NT 6.1;WOW64) AppleWebKit/537.36(KABUL, like Gecko) "
                            "Chrome/86.0.4240.198Safari/537.36 "
        }
resp = requests.get(url=url, headers=headers)

e = etree.HTML(resp.text)
images_shu = e.xpath("//div[@class='tab-cont'][2]/div/div/div/a/@href")
# for i in images_shu:
#     print(i)

lst_2 = []
for url in images_shu:
    # print(url)
    imges_1 =url.split('/')
    if imges_1[-1][:-4] == "1080x1920":
        lst_2.append(url)

for url in lst_2:
    # print(url)
    time.sleep(1)
    resp = requests.get(url, headers=headers)
    file_name = url[url.rindex('picture'):url.rindex('/')].replace('/', '_')+ '.jpg'
    # print(file_name)
    print("正在保存："+ file_name+ "壁纸")
    with open(f'02-shu/{file_name}', 'wb') as f:
        f.write(resp.content)

print("全部保存完毕")