[Python] 纯文本查看 复制代码
"""
************************************
@version: 0.1
@author: zayki
@contact: [url=mailto:zyj_super@outlook.com]zyj_super@outlook.com[/url]
@file: zhuoku_spider.py
@time: 2022/2/27 15:24
************************************
"""
import os
import requests
from lxml import etree
from os.path import splitext,dirname,basename
import re
target_url = "http://www.zhuoku.com/"
headers = {
"Upgrade-Insecure-Requests": "1",
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh-CN,zh;q=0.9",
"Connection": "close"
}
response = requests.get(target_url, headers = headers,verify = False,timeout = 5)
result = etree.HTML(response.content.decode('GBK'))
last_bizhi_urls = result.xpath('//div[@id="bizhititle"]//li//@href')
last_bizhi_titles = result.xpath('//div[@id="bizhititle"]//li//a')
pic_urls = []
savepath = os.getenv("USERPROFILE") + "\\desktop\\"
def get_proxy():
return requests.get("http://118.24.52.95:5010/get/").json() # 参考https://github.com/jhao104/proxy_pool搭建一个获取代{过}{滤}理的服务器即可。
def get_pic_urls(url):
sub_url = target_url + url
pic_urls.append(sub_url)
proxy_ip = get_proxy()['proxy']
print(proxy_ip)
proxies = {"https://":proxy_ip,"http://":proxy_ip}
print(sub_url)
subresponse = requests.get(sub_url, headers=headers, verify=False,proxies = proxies, timeout=5)
subresult = etree.HTML(subresponse.content.decode('GBK'))
last_link_name = subresult.xpath('//div[@class="turn"]//select//@value')[-1]
last_link = dirname(sub_url)+ '/' + last_link_name
link_name, countlinks = splitext(last_link_name)[0].split('_')[0],splitext(last_link_name)[0].split('_')[-1]
last_link_response = requests.get(last_link, headers=headers, verify=False, proxies = proxies, timeout=5)
last_link_result = etree.HTML(last_link_response.content.decode('GBK'))
last_pic_link = last_link_result.xpath('//div[@class="bizhiin"]//a/@href')[-1]
p1 = re.compile(r'[(](.*?)[)]', re.S)
pic_links_count = re.findall(p1, last_pic_link)[0]
for index in range(1,int(pic_links_count) + 1):
try:
proxy_ip = get_proxy()['proxy']
print(proxy_ip)
proxies = {"https://": proxy_ip, "http://": proxy_ip}
pic_url_link = dirname(sub_url) + "/" + link_name + "(" + str(index) + ")" + ".htm"
pic_url_link_resq = requests.get(pic_url_link, headers=headers, verify=False,proxies = proxies, timeout=5)
pic_url_link_html = etree.HTML(pic_url_link_resq.content.decode('GBK'))
target_pic_link = pic_url_link_html.xpath('//img[@id="imageview"]//@src')[0]
headers_pic = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/98.0.4758.102 Safari/537.36",
"Accept": "*/*",
"Referer": pic_url_link,
"Accept-Encoding": "gzip, deflate",
"Accept-Language": "zh-CN,zh;q=0.9",
"Connection": "close"
}
target_pic_link_resq = requests.get(target_pic_link, headers=headers_pic, verify=False,proxies = proxies, timeout=5)
file_name = basename(target_pic_link)
try:
os.mkdir(savepath + link_name)
except:
pass
try:
with open(savepath + link_name + "\\" + file_name,'wb') as file:
file.write(target_pic_link_resq.content)
print(target_pic_link)
print("The image {0} has been saved in local path {1}".format(file_name,savepath + link_name))
except Exception as e:
print("index:" + index +" "+ str(e))
except Exception as e:
print(e)
url = last_bizhi_urls[0]
get_pic_urls(url)
[复制链接]
发表于 2022-3-12 18:05
|
发表于 2022-3-16 13:33
