trixiebooru.org)图片

11个月前更新

2032

先附上源代码：

import requests
import re
import time
import random

search=str(input("search syntax:"))
page1=int(input("start-page:"))
page2=int(input("end-page:"))
path=str(input("path:"))

try:
    i=page1
    for i in range(page1,page2+1):
        print("page:"+str(i))
        derpy="derpicdn.net"
        search_url="https://trixiebooru.org/search?sd=desc&sf=score&page="+str(i)+"&q="+search
        headers={
                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:109.0) Gecko/20100101 Firefox/117.0",
                    "cookie":"filter_id=100073"
        }
        results1=requests.get(url=search_url,headers=headers)
        pattern1=re.compile(r'https://[^\s<>"]+[^\s<>"]')
        s1=pattern1.findall(results1.text)

        targets1 = []
        id = []
        date_id = []
        targets2 = []
        type = []

        for i in range(0,len(s1)):
            index1=s1[i].find(derpy)
            if index1!=-1:
                #print(s1[i][-9:-4])
                if s1[i][-2:]!=";}" and s1[i][-2:]!=";]":
                    print(s1[i])
                    targets1.append(s1[i])
                    type.append(s1[i][-3:])
        for target in targets1:
            match1=re.search(r"img(.*)/t",target)
            if match1:
                original_number=match1.group()
                num1=original_number.replace("/t","")
                num2=num1.replace("img","")
                #print(num2)
                date_id.append(num2)

                match2=re.search(r'\/([^\/]+)$',num2)
                id.append(match2.group(1))
        #print(len(id))
        #print(len(date_id))
        original_url="https://trixiebooru.org/images/"
        for j in range(0,len(id)):
            url1=original_url+id[j]
            key=id[j]+"__"
            results2=requests.get(url=url1, headers=headers)

            if type[j]=="gif":
                pattern2=re.compile(key + r"(.*?)\.gif")
                s2=pattern2.findall(results2.text)
                #print("s:"+str(len(s2)))
                if len(s2)==2:
                    s=s2[0]+"."+type[j]
                    #print(s)
                    target_url="https://derpicdn.net/img/view"+date_id[j]+s
                    targets2.append(target_url)
                    print("正在获取第"+str(j+1)+"个目标...")
                    i+=1
            if type[j]=="png":
                pattern3=re.compile(key + r"(.*?)\.png")
                s3=pattern3.findall(results2.text)
                #print("s:"+str(len(s3)))
                if len(s3)==2:
                    s=s3[0]+"."+type[j]
                    #print(s)
                    target_url="https://derpicdn.net/img/view"+date_id[j]+s
                    targets2.append(target_url)
                    print("正在获取第"+str(j+1)+"个目标...")
                    i+=1
            if type[j]=="jpg":
                pattern4=re.compile(key + r"(.*?)\.jpg")
                s4=pattern4.findall(results2.text)
                #print("s:"+str(len(s4)))
                if len(s4)==2:
                    s=s4[0]+"."+type[j]
                    #print(s)
                    target_url="https://derpicdn.net/img/view"+date_id[j]+s
                    targets2.append(target_url)
                    print("正在获取第"+str(j+1)+"个目标...")
                    i+=1

        for target in targets2:
            print("target:"+target)
            print("downloading...")
            n1=random.randint(10000,99999)
            n2=random.randint(10000,99999)
            test=requests.get(url=target,headers=headers)
            pictrue=str(n1)+str(n2)+"."+target[-3:]
            with open(path+"\"+pictrue,"wb") as t:
                t.write(test.content)
                print("Done!")
                time.sleep(1)
except:
    print("download error!")

#default:100073
#everything:56027

此脚本需要本地搭建python环境，复制源代码到文件，改后缀为py。