mirror of
https://gitee.com/Lyon1998/pikapython.git
synced 2025-01-15 17:02:53 +08:00
103 lines
3.3 KiB
Plaintext
103 lines
3.3 KiB
Plaintext
# 导入selenium包
|
|
import os.path
|
|
import pickle
|
|
import re
|
|
from time import sleep
|
|
from selenium import webdriver
|
|
from bs4 import BeautifulSoup
|
|
import requests
|
|
|
|
# 初始化一个引用计数，用于后面的图片简单命名
|
|
index = 0
|
|
# 设置代理服务器端口
|
|
proxies = {'https':'http://127.0.0.1:10900'}
|
|
|
|
next_url = ''
|
|
# 定义爬虫方法
|
|
def geturl(url):
|
|
# 创建浏览器对象
|
|
browser = webdriver.Firefox(executable_path="D:\GeckoDriver\geckodriver.exe")
|
|
# 设置要爬取的网站
|
|
browser.get(url)
|
|
# css获得对应html形成列表
|
|
s = browser.find_elements_by_css_selector("div[class='post-preview-container'] a")
|
|
pic = s[:]
|
|
for i in pic:
|
|
# print(i)
|
|
huoqvpicture(str(i.get_attribute("href")))
|
|
sleep(1)
|
|
print("翻页")
|
|
# 获取下一页的链接
|
|
link = browser.find_elements_by_css_selector("div[class='paginator numbered-paginator mt-8 mb-4 space-x-2 flex justify-center items-center'] a")
|
|
# print(str(link[-1].get_attribute("href")))
|
|
# 将下一页链接的值赋给next_url
|
|
next_url = str(link[-1].get_attribute("href"))
|
|
browser.close()
|
|
# print(next_url)
|
|
geturl(next_url)
|
|
|
|
def huoqvpicture(url):
|
|
browser = webdriver.Firefox(executable_path="D:\GeckoDriver\geckodriver.exe")
|
|
# global index
|
|
browser.get(url)
|
|
n = browser.find_elements_by_css_selector("section[id='content'] section")
|
|
try:
|
|
s = browser.find_elements_by_css_selector("div[class='notice notice-small post-notice post-notice-resized'] a")
|
|
print(str(s[-1].get_attribute("href")))
|
|
DownLoadPicture(str(s[-1].get_attribute("href")), str(n[0].get_attribute("data-id")))
|
|
# index = 0
|
|
except:
|
|
p = browser.find_elements_by_css_selector("section[class='image-container note-container blacklisted'] picture img")
|
|
print(str(p[-1].get_attribute("src")))
|
|
DownLoadPicture(str(p[-1].get_attribute("src")), str(n[0].get_attribute("data-id")))
|
|
# index = 1
|
|
# 确定图片格式
|
|
# print(index)
|
|
# 定位original picture链接所在位置
|
|
# print(s[-1].get_attribute("src"))
|
|
# 打印链接地址
|
|
#图片名称
|
|
|
|
sleep(1)
|
|
print(str(n[0].get_attribute("data-id")))
|
|
browser.close()
|
|
|
|
def DownLoadPicture(url,name):
|
|
root = "./picture/"
|
|
path1 =root + name + '.jpg'
|
|
path2 =root + name + '.png'
|
|
# 若文件是.jpg 格式
|
|
try:
|
|
if not os.path.exists(root):
|
|
os.mkdir(root)
|
|
if not os.path.exists(path1):
|
|
sleep(1)
|
|
r = requests.get(url,proxies=proxies)
|
|
print(r.status_code)
|
|
with open(path1, 'wb') as f:
|
|
f.write(r.content)
|
|
f.close()
|
|
print("文件保存成功")
|
|
else:
|
|
print("文件已存在")
|
|
# 若文件是.png 格式
|
|
except:
|
|
if not os.path.exists(root):
|
|
os.mkdir(root)
|
|
if not os.path.exists(path2):
|
|
sleep(1)
|
|
r = requests.get(url, proxies=proxies)
|
|
print(r.status_code)
|
|
with open(path2, 'wb') as f:
|
|
f.write(r.content)
|
|
f.close()
|
|
print("文件保存成功")
|
|
else:
|
|
print("文件已存在")
|
|
sleep(1)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
url = "https://danbooru.donmai.us/"
|
|
geturl(url)
|