目标网站 https://divnil.com
首先看看这网站是怎样加载数据的;
image
当然在学习Python的道路上肯定会困难，没有好的学习资料，怎么去学习呢？ 学习Python中有不明白推荐加入交流群号：973783996 群里有志同道合的小伙伴，互帮互助， 群里有不错的视频学习教程和PDF！
打开网站后发现底部有下一页的按钮，ok，爬这个网站就很简单了;
img
我们目标是获取每张图片的高清的源地址，并且下载图片到桌面;先随便打开一张图片看看详细;
emmm，只有一张图
img
看起来还挺清晰的，单击新窗口打开图片
img
然后下载图片，说实话，这图片很小，我很担心不是高清原图(管他的);
img
PS:一定要禁用广告拦截插件，不然加载不出图，我就在这被坑T_T;
img
接着分析我们从何入手
1、先去主页面获取每个图片的详细页面的链接
这链接还是比较好获取的，直接 F12 审核元素，或者右键查看代码，手机上chrome和firefox在url前面加上 "view-source"
比如： view-source:https://www.baidu.com/
img
2、从详细页面获取图片大图地址
随便打开一个图片详细页面如图：
img
接着按 F12 审核元素，我们需要定位该图片的链接，首先单击左上角的这玩意儿，像一个鼠标的图标：
img
接着只需要单击网页上的图片就能定位到代码了：
img
3、用大图地址下载该图片
这个很简单，看代码
先安装 Requests 和 BeautifulSoup 库
pip install requests bs4
导入库
import requestsfrom bs4 import BeautifulSoupimport sys
请求获取网页源代码
url = "https://divnil.com/wallpaper/iphone8/%E3%82%A2%E3%83%8B%E3%83%A1%E3%81%AE%E5%A3%81%E7%B4%99_2.html"
headers = {
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:58.0) Gecko/20100101 Firefox/58.0",
}
resp = requests.get(url, headers=headers)
if resp.status_code != requests.codes.OK:
print("Request Error, Code: %d"% resp.status_code)
sys.exit()
然后解析出所有图片的详细地址
soup = BeautifulSoup(resp.text, "html.parser")
contents = soup.findAll("div", id="contents")[0]
wallpapers = contents.findAll("a", rel="wallpaper")
links = []
for wallpaper in wallpapers:
links.append(wallpaper[href])
接着在详细网页里获取那个看似高清的图片的不确定是否为真实图片链接并下载(/滑稽)
import os
head = "https://divnil.com/wallpaper/iphone8/"
if os.path.exists("./Divnil") != True:
os.mkdir("./Divnil")
for url in links:
url = head + url
resp = requests.get(url, headers=headers)
if resp.status_code != requests.codes.OK:
print("URL: %s REQUESTS ERROR. CODE: %d" % (url, resp.status_code))
continue
soup = BeautifulSoup(resp.text, "html.parser")
img = soup.find("div", id="contents").contents.find("img", id="main_content")
img_url = head + img["original].replace("../", "")
img_name = img[alt]
print("start download %s ..." % img_url)
resp = requests.get(img_url, headers=headers)
if resp.status_code != requests.codes.OK:
print("IMAGE %s DOWNLOAD FAILED." % img_name)
with open("./Divnil/" + img_name + ".jpg", "wb") as f:
f.write(resp.content)
img
主要代码
img
完成，贴上所有代码
import requests
from bs4 import BeautifulSoup
import sys
import os
class Divnil:
def __init__(self):
self.url = "https://divnil.com/wallpaper/iphone8/%E3%82%A2%E3%83%8B%E3%83%A1%E3%81%AE%E5%A3%81%E7%B4%99.html"
self.head = "https://divnil.com/wallpaper/iphone8/"
self.headers = {
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:58.0) Gecko/20100101 Firefox/58.0",
}
def getImageInfoUrl(self):
resp = requests.get(self.url, headers=self.headers)
if resp.status_code != requests.codes.OK:
print("Request Error, Code: %d"% resp.status_code)
sys.exit()
soup = BeautifulSoup(resp.text, "html.parser")
contents = soup.find("div", id="contents")
wallpapers = contents.findAll("a", rel="wallpaper")
self.links = []
for wallpaper in wallpapers:
self.links.append(wallpaper[href])
def downloadImage(self):
if os.path.exists("./Divnil") != True:
os.mkdir("./Divnil")
for url in self.links:
url = self.head + url
resp = requests.get(url, headers=self.headers)
if resp.status_code != requests.codes.OK:
print("URL: %s REQUESTS ERROR. CODE: %d" % (url, resp.status_code))
continue
soup = BeautifulSoup(resp.text, "html.parser")
img = soup.find("div", id="contents").find("img", id="main_content")
img_url = self.head + img[original].replace("../", "")
img_name = img[alt]
print("start download %s ..." % img_url)
resp = requests.get(img_url, headers=self.headers)
if resp.status_code != requests.codes.OK:
print("IMAGE %s DOWNLOAD FAILED." % img_name)
continue
if / in img_name:
img_name = img_name.split(/)[1]
with open("./Divnil/" + img_name + ".jpg", "wb") as f:
f.write(resp.content)
def main(self):
self.getImageInfoUrl()
self.downloadImage()
if __name__ == "__main__":
divnil = Divnil()
divnil.main()
网友评论