爬虫p站，下载喜欢的博主所有作品——7月2日

url获得的图片所有链接以
url = ‘https://www.pixiv.net/ajax/user/20365605/profile/all’ 获取
就只需要修改中间的数字

获得到了图片详情页的特定数字，就可拼出详情页的url，url = 'https://www.pixiv.net/ajax/illust/' + str(特定的数字)

import requests
import time

def download_img(url):  # 获取到图片url后定义个函数用于下载
    headers_download = {
        "referer": "https://www.pixiv.net/"
        # 这里携带referer因为p站的图片链接都是防盗链
        # 只要加上这个链接就会认为你是从p站访问过来的就会让你正常访问了
    }
    response = requests.get(url=url, headers=headers_download)
    name = url.split("/")[-1]
    # 将图片链接以斜杠分割后取最后面的信息作为名字，因为爬取的图片有jeg也有png
    with open("./png/" + name, "wb") as f:  # 创建一个以图片链接对应名字的文件，需要自己创建png目录
        f.write(response.content)  # 将图片二进制数据存入，图片也就得到了
    print(name + "下载成功")


url = 'https://www.pixiv.net/ajax/user/20365605/profile/all' 
headers = {
    'User-Agent':
        '你的user—agent',
    'Cookie': '你的cookie'
    , "referer": "https://www.pixiv.net/"
}
params = {
    'lang': 'zh',
    'version': '8a10a9007b94f71b617fe580e88bd087c13a8994',
}
html = requests.get(url=url, headers=headers, params=params).json()
print(type(html))
# 提取博主所有作品的图片特定数字链接
urls = html['body']['illusts']
print(urls)
key_id_list = []
for number, key in enumerate(urls.keys(), start=1):
    print(key)
    key_id_list.append(int(key))
    print(number)
print(key_id_list)
time.sleep(2)#休息两秒

# 得到所有图片的链接
url = 'https://www.pixiv.net/ajax/user/20365605/profile/illusts'
params = {
    'ids[]': key_id_list[:48],
    'work_category': 'illustManga',
    'is_first_page': 1,
    'lang': 'zh',
    'version': '8a10a9007b94f71b617fe580e88bd087c13a8994',
}
img_all_url = requests.get(url=url, headers=headers, params=params).json()
print(img_all_url)
##下载缩略图
# numeric_values = [value['url'] for key, value in img_all_url['body']['works'].items() if key.isdigit()]
# print(numeric_values)
# print(len(numeric_values))
# for index,i in enumerate(numeric_values,start=1):
#     print(index,"图片正在下载中")
#     download_img(i)
#     time.sleep(1)
#     print(index,"图片下载完成")
# 下载原图
for index, i in enumerate(key_id_list, start=1):
    print(index, "图片正在下载中")
    url = 'https://www.pixiv.net/ajax/illust/' + str(i)
    img_json = requests.get(url=url, headers=headers).json()
    urls = img_json['body']['urls']['original']
    download_img(urls)
    time.sleep(2)
    print(index, "图片下载完成")
# download_img(urls)
# 下载图片


# with open('pixiv.html','w',encoding='utf-8') as f:
#     f.write(html)

参考文章
参考文章：https://zhuanlan.zhihu.com/p/557657010