爬取p站插图

爬取p站插图的爬虫

直接看代码，和以前一样cookie需要自己放

代码片

import requests,re,time
re1 = re.compile(r'"id":"(?P<id>.*?)".*?title".*?illustType.*?xRestrict".*?',re.S)
re2 = re.compile(r'"original".*?"(?P<url2>.*?)"},.*?tags.*?:',re.S)
headers = {
    "Cookie":"",
    "Referer":"https://www.pixiv.net/tags/%E3%83%96%E3%83%AB%E3%83%BC%E3%82%A2%E3%83%BC%E3%82%AB%E3%82%A4%E3%83%96/artworks?p=19&s_mode=s_tag",
    "Sec-Ch-Ua":'"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36",
    "X-User-Id":"103320984"
}
headers1 = {
    "Cookie":"",
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"
}
headers2 = {
    "Referer":"https://www.pixiv.net/",
    "Sec-Ch-Ua":'"Chromium";v="122", "Not(A:Brand";v="24", "Google Chrome";v="122"',
    "Sec-Ch-Ua-Mobile":"?0",
    "Sec-Ch-Ua-Platform":'"Windows"',
    "Sec-Fetch-Dest":"document",
    "Sec-Fetch-Mode":"navigate",
    "Sec-Fetch-Site":"cross-site",
    "Sec-Fetch-User":"?1",
    "Upgrade-Insecure-Requests":"1",
    "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/122.0.0.0 Safari/537.36"

}
word = input("请输入查找内容：")
mode = input("r18 , safe or all")
for a in range(1,100):
    url = f"https://www.pixiv.net/ajax/search/artworks/{word}?word={word}&order=date_d&mode={mode}&p={a}&csw=0&s_mode=s_tag&type=all&lang=zh&version=605ecf6eaed036511e8b3bd1dd2430e1bd0e0b07"
    response = requests.get(url, headers=headers)
    print(f'第{a}页')
    print(response.text)
    list_id =re1.finditer(response.text)
    for it in list_id:
        id = it.group("id")
        # id = id.replace('\\', '')
        print(id)
        url2 = f'https://www.pixiv.net/artworks/{id}'
        response2 = requests.get(url2,headers = headers1)
        jpg1 = re2.finditer(response2.text)
        response2.close()
        time.sleep(2)
        for i in jpg1:
            url1 = i.group("url2")
            print(url1)
            response3 = requests.get(url1,headers = headers2)
            with open(f"图片/{id[-8:]}.jpg", mode="wb") as f:
                f.write(response3.content)
            response3.close()

预览图已经没了