话不多说直接上代码，都有注释，如果有不懂的可以提出来或者有更好方案也可以提出来，大家一起学习。
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import requests
import urllib.parse
from lxml import etree
import re
import os
# 自定义错误
class Error(Exception):
def __init__(self, message):
self.message = message
class Wallpaper:
"""
0x0 所有分辨率
1920x1080
"""
def __init__(self, url, path, page, min_resolution):
self.url = url
self.path = path
self.params = {
"page": page
}
self.min_resolution = min_resolution
# post请求参数
self.data = {
# 分页
"view": "paged",
# 分辨率
"min_resolution": min_resolution,
# 分辨率等于还是至少是 可以大于等于
"resolution_equals": "=",
# 排序方法
# newest 最新上传
# rating 最多赞数
"sort": "newest",
}
# 创建文件夹
@staticmethod
def create_dir(path):
if not os.path.exists(path):
os.makedirs(path)
else:
return "文件夹已存在"
# 返回图片类型的文件夹名称, 根据链接的不同类型
def get_folder_name(self):
# 标签链接名称获取 https://wall.alphacoders.com/tag/ahri-(league-of-legends)-wallpapers?lang=Chinese
pattern = r"tag/([\w-]+)-(.*)\?lang=Chinese"
match = re.search(pattern, self.url)
if match:
content1 = match.group(1) # 获取第一个捕获组的内容
content2 = match.group(2) # 获取第二个捕获组的内容
image_dir_name = content1 + content2
return image_dir_name
# 分类链接名称获取 https://wall.alphacoders.com/by_sub_category.php?id=169908&name=%E8%8B%B1%E9%9B%84%E8%81%94%E7%9B%9F+%E5%A3%81%E7%BA%B8&lang=Chinese
elif not match:
try:
params = {}
url_params = self.url.split("?")[1]
temp = url_params.split("&")
for param in temp:
key = param.split("=")[0]
value = param.split("=")[1]
params[key] = value
name = params.get("name", None)
# 获取分类名称
if name is not None:
image_dir_name = urllib.parse.unquote(name.split("+")[0])
return image_dir_name
# 获取不到名称名称，那链接中的就是这种类型 https://wall.alphacoders.com/by_resolution.php?w=3840&h=2160&lang=Chinese
else:
w = params.get("w")
h = params.get("h")
image_dir_name = w + "x" + h
return image_dir_name
# 获取索引名称 https://wall.alphacoders.com/search.php?search=landscape&lang=Chinese
except AttributeError:
pattern = r"search=([^&]+)&lang=Chinese"
match = re.search(pattern, self.url)
if match:
image_dir_name = match.group(1)
return image_dir_name
# 获取每一页的所有图片页面的图片链接
def get_image_urls(self):
url = "https://wall.alphacoders.com"
response = requests.post(self.url, params=self.params, data=self.data, allow_redirects=False)
# 超出页数会重定向到最大的页面,进行判断,防止重复爬取
if response.status_code == 200:
html = etree.HTML(response.text)
image_page_params = html.xpath(
'//*[@id="page_container"]//div//div[@class="thumb-container"]//div[@class="boxgrid"]//@href')
# 判断当前页面有没有图片
if len(image_page_params) == 0:
raise Error("获取不到当前页码的图片，请检查页码有否有效！")
else:
result = []
for image_page_param in image_page_params:
image_page_url = url + image_page_param
response_image = requests.get(image_page_url).text
html = etree.HTML(response_image)
image_urls = html.xpath("/html/body/div[2]/div[2]/div[2]/div[1]/img//@src")
# 这里可以用推导式
for i in image_urls:
result.append(i)
return len(result), result
raise Error("获取不到当前页码的图片，请检查页码有否有效！")
def download_image(self):
mun = 0
error = 0
self.create_dir(self.path)
images_dir_name = self.get_folder_name()
images_mun, images_urls = self.get_image_urls()
for image_url in images_urls:
image_name_temp = re.search(r'https://[^/]+/[^/]+/(\d+)(\.png|\.jpg)', image_url)
# 匹配图片页面的图片是否是这两种格式,不是则跳过
if image_name_temp is not None:
image_name = image_name_temp.group(1)
# 判断图片是否重复下载
if not os.path.exists(os.path.join(self.path, images_dir_name, image_name + ".png")):
self.create_dir(os.path.join(self.path, images_dir_name))
download = requests.get(image_url).content
with open(os.path.join(self.path, images_dir_name, image_name + ".png"), "wb") as f:
f.write(download)
print("图片 {} 下载完成,图片地址: {}".format(image_name, image_url))
mun = mun + 1
if mun == images_mun:
print("当前页面图片下载完成, 一共 {} 张图片".format(mun))
else:
print("已有图片: {}, 图片地址: {}".format(image_name, image_url))
continue
else:
error = error + 1
print("下载失败 {} 张图片".format(error))
if __name__ == '__main__':
url = input("请输入壁纸url! \n")
# 存放图片的文件夹
path = "images"
'''
分辨率
0x0 所有分辨率
'''
print("""
常用分辨率
1920x1080
2560x1440
2560x1600
3840x2160
5120x2880
7680x4320
""")
resolution = input("请输入需要下载的分辨率! \n")
# 200 可以修为自己想怕的最大页数，当链接所有页数大于或小于都能正常爬取链接的最大页数的图片，这里可以取一个折中的值
for page_num in range(1, 200):
print("正在下载第 {} 页的图片".format(page_num))
page_one = Wallpaper(url, path, str(page_num), resolution)
print(page_one.data)
