python实例：爬取caoliu图片，同时下载到指定的文件夹内

def stepa (AA):
    lit=[]
    for url in AA:
        response = requests.get(url=url, headers=headers, timeout=100000)
        wb_data = response.text.encode(‘iso-8859-1‘).decode(‘gbk‘)#caoliu的编码格式需要对返回值重新转码
        # 将页面转换成文档树
        html = etree.HTML(wb_data)
        a = html.xpath(‘//td[@class="tal"]//@href‘)#帖子地址xpath
        lit.append(a)
    return(lit) 
alllink = stepa(AA)
alllink=alllink[0]

def stepb(alllink,headers,BB):
    for url in alllink:
        #print(url)
        if "read"  in url:
            continue
        elif url in BB:
            continue
        else:
            url=‘https://cl.hexie.xyz/‘+url
            print(url)
            response = requests.get(url, headers=headers)
            response=response.text.encode(‘iso-8859-1‘).decode(‘gbk‘)
            html = etree.HTML(response)
            b = html.xpath(‘//div[@class="tpc_content do_not_catch"]//@ess-data‘)#图片地址xpath
            title = html.xpath(‘/html/head/title/text()‘)#帖子名称xpath
            title=title[0]
            title=title[:-27]#去掉帖子名称后面共同的和影响创建文件夹的部分
            print(title)

# -*-coding:utf8-*-
# encoding:utf-8
# 本脚本用于爬取草榴图片板块（新时代的我们）最近3天的所有帖子的所有图片，每一个帖子创建独立的文件夹，图片下载到文件夹中
import requests
from lxml import etree
import os
import sys
import re
import random
from urllib import request
import io

#sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding=‘utf8‘)
#解决vscode窗口输出乱码的问题，需要import io 和import sys

headers = {
    ‘authority‘: ‘cl.hexie.xyz‘,
    ‘upgrade-insecure-requests‘: ‘1‘,
    ‘user-agent‘: ‘Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.88 Safari/537.36‘,
    ‘accept‘: ‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9‘,
    ‘sec-fetch-site‘: ‘none‘,
    ‘sec-fetch-mode‘: ‘navigate‘,
    ‘accept-language‘: ‘zh-CN,zh;q=0.9‘,
    ‘cookie‘: ‘__cfduid=d9b8dda581516351a1d9d388362ac222c1603542964‘,
}    

path = os.path.abspath(os.path.dirname(sys.argv[0]))

AA=[
    "https://cl.和谐.xyz/thread0806.php?fid=8",
   #"https://cl.和谐.xyz/thread0806.php?fid=8&search=&page=2",
   #"https://cl.和谐.xyz/thread0806.php?fid=8&search=&page=3"
    ]

#AA里包含最新前3页列表链接

BB=["htm_data/1109/8/594739.html",
    "htm_data/1803/8/3018643.html",
    "htm_data/0706/8/36794.html",
    "htm_data/1106/8/524775.html",
    "htm_data/2011/8/344500.html"]

#BB里面包含需要跳过的帖子，这部分帖子是站务贴，里面没资源

#第1步，获取每一页所有的帖子地址，地址格式“https://cl.和谐.xyz/htm_data/2011/8/4182841.html”
def stepa (AA):
    lit=[]
    for url in AA:
        response = requests.get(url=url, headers=headers, timeout=100000)
        wb_data = response.text.encode(‘iso-8859-1‘).decode(‘gbk‘)#草榴的编码格式需要对返回值重新转码
        # 将页面转换成文档树
        html = etree.HTML(wb_data)
        a = html.xpath(‘//td[@class="tal"]//@href‘)#帖子地址xpath
        lit.append(a)
    return(lit) 
alllink = stepa(AA)
alllink=alllink[0]

#第2步，获取每一篇帖子里所有图片的地址，地址格式“https://和谐.xyz/i/2020/11/15/sedlrk.jpg"
def stepb(alllink,headers,BB):
    for url in alllink:
        #print(url)
        if "read"  in url:
            continue
        elif url in BB:
            continue
        else:
            url=‘https://cl.和谐.xyz/‘+url
            print(url)
            response = requests.get(url, headers=headers)
            response=response.text.encode(‘iso-8859-1‘).decode(‘gbk‘)
            html = etree.HTML(response)
            b = html.xpath(‘//div[@class="tpc_content do_not_catch"]//@ess-data‘)#图片地址xpath
            title = html.xpath(‘/html/head/title/text()‘)#帖子名称xpath
            title=title[0]
            title=title[:-27]#去掉帖子名称后面共同的和影响创建文件夹的部分
            print(title)

            path2 = r‘D://tu‘ 
            os.mkdir(path2 + ‘./‘+str(title))
            #以上两行即在d盘tu目录下创建名称为变量title的文件夹

            for c in b:
                print("loading"+" " +c)
                pic_name = random.randint(0,100)#图片名称随机命令

                r = requests.get(c,stream=True,headers=headers)
                time = r.elapsed.total_seconds()#获取响应时间
                if time > 1000:
                    continue
                else:
                    with open(path2 + ‘./‘+str(title) +‘./‘+str(pic_name) +‘.jpg‘, ‘wb‘) as fd:
                        for chunk in r.iter_content():
                            fd.write(chunk)
                #从87行开始即下载的脚本，把图片下载到上文创建的指定文件夹中

stepb(alllink,headers,BB)

#第3步：提示爬取完成
def over():
    print("ok")
over()