def makefolder(id): # 根據(jù)畫師的id創(chuàng)建對(duì)應(yīng)的文件夾
	try:
		folder = os.path.join('E:\pixivimages', id)
		os.mkdir(folder)
		return folder
	except(FileExistsError):
		print('the folder exists!')
		exit()

def getAuthorAllPicID(id, cookie): # 獲取畫師所有圖片的id
	url = 'https://pixiv.net/ajax/user/' + id + '/profile/all' # 訪問(wèn)存有畫師所有作品
	headers = {
		'User-Agent': user_agent,
		'Cookie': cookie,
		'Referer': 'https://www.pixiv.net/artworks/' 
		# referer不能缺少，否則會(huì)403
	}
	res = requests.get(url, headers=headers, proxies=proxies)
	if res.status_code == 200:
		resdict = json.loads(res.content)['body']['illusts'] # 將json轉(zhuǎn)化為python的字典后提取元素
		return [key for key in resdict] # 返回所有圖片id
	else:
		print("Can not get the author's picture ids!")
		exit()

def getPictures(folder, IDlist, cookie): # 訪問(wèn)圖片儲(chǔ)存的真實(shí)網(wǎng)址
	for picid in IDlist:
		url1 = 'https://www.pixiv.net/artworks/{}'.format(picid) # 注意這里referer必不可少,否則會(huì)報(bào)403
		headers = {
			'User-Agent': user_agent,
			'Cookie': cookie,
			'Referer': url1
		}
		url = 'https://www.pixiv.net/ajax/illust/' + str(picid) + '?lang = zh' #訪問(wèn)儲(chǔ)存圖片網(wǎng)址的json
		res = requests.get(url, headers=headers, proxies=proxies)
		if res.status_code == 200:
			data = json.loads(res.content)
			picurl = data['body']['urls']['original'] # 在字典中找到儲(chǔ)存圖片的路徑與標(biāo)題
			title = data['body']['title']
			title = changeTitle(title) # 調(diào)整標(biāo)題
			print(title)
			print(picurl)
			download(folder, picurl, title, headers)
		else:
			print("Can not get the urls of the pictures!")
			exit()


def changeTitle(title): # 為了防止
	global i
	title = re.sub('[*:]', "", title) # 如果圖片中有下列符號(hào),可能會(huì)導(dǎo)致圖片無(wú)法成功下載
	# 注意可能還會(huì)有許多不能用于文件命名的符號(hào),如果找到對(duì)應(yīng)符號(hào)要將其添加到正則表達(dá)式中
	if title == '無(wú)題': # pixiv中有許多名為'無(wú)題'(日文)的圖片,需要對(duì)它們加以區(qū)分以防止覆蓋
		title = title + str(i)
		i = i + 1
	return title


def download(folder, picurl, title, headers): # 將圖片下載到文件夾中
	img = requests.get(picurl, headers=headers, proxies=proxies)
	if img.status_code == 200:
		with open(folder + '\\' + title + '.jpg', 'wb') as file: # 保存圖片
			print("downloading:" + title)
			file.write(img.content)
	else:
		print("download pictures error!")

import requests
from fake_useragent import UserAgent
import json
import re
import os

global i
i = 0
ua = UserAgent() # 生成假的瀏覽器請(qǐng)求頭,防止被封ip
user_agent = ua.random # 隨機(jī)選擇一個(gè)瀏覽器
proxies = {'http': 'http://127.0.0.1:51837', 'https': 'http://127.0.0.1:51837'} # 代理,根據(jù)自己實(shí)際情況調(diào)整,注意在請(qǐng)求時(shí)一定不要忘記代理!!


def makefolder(id): # 根據(jù)畫師的id創(chuàng)建對(duì)應(yīng)的文件夾
	try:
		folder = os.path.join('E:\pixivimages', id)
		os.mkdir(folder)
		return folder
	except(FileExistsError):
		print('the folder exists!')
		exit()


def getAuthorAllPicID(id, cookie): # 獲取畫師所有圖片的id
	url = 'https://pixiv.net/ajax/user/' + id + '/profile/all' # 訪問(wèn)存有畫師所有作品
	headers = {
		'User-Agent': user_agent,
		'Cookie': cookie,
		'Referer': 'https://www.pixiv.net/artworks/' 
	}
	res = requests.get(url, headers=headers, proxies=proxies)
	if res.status_code == 200:
		resdict = json.loads(res.content)['body']['illusts'] # 將json轉(zhuǎn)化為python的字典后提取元素
		return [key for key in resdict] # 返回所有圖片id
	else:
		print("Can not get the author's picture ids!")
		exit()


def getPictures(folder, IDlist, cookie): # 訪問(wèn)圖片儲(chǔ)存的真實(shí)網(wǎng)址
	for picid in IDlist:
		url1 = 'https://www.pixiv.net/artworks/{}'.format(picid) # 注意這里referer必不可少,否則會(huì)報(bào)403
		headers = {
			'User-Agent': user_agent,
			'Cookie': cookie,
			'Referer': url1
		}
		url = 'https://www.pixiv.net/ajax/illust/' + str(picid) + '?lang = zh' #訪問(wèn)儲(chǔ)存圖片網(wǎng)址的json
		res = requests.get(url, headers=headers, proxies=proxies)
		if res.status_code == 200:
			data = json.loads(res.content)
			picurl = data['body']['urls']['original'] # 在字典中找到儲(chǔ)存圖片的路徑與標(biāo)題
			title = data['body']['title']
			title = changeTitle(title) # 調(diào)整標(biāo)題
			print(title)
			print(picurl)
			download(folder, picurl, title, headers)
		else:
			print("Can not get the urls of the pictures!")
			exit()


def changeTitle(title): # 為了防止
	global i
	title = re.sub('[*:]', "", title) # 如果圖片中有下列符號(hào),可能會(huì)導(dǎo)致圖片無(wú)法成功下載
	# 注意可能還會(huì)有許多不能用于文件命名的符號(hào),如果找到對(duì)應(yīng)符號(hào)要將其添加到正則表達(dá)式中
	if title == '無(wú)題': # pixiv中有許多名為'無(wú)題'(日文)的圖片,需要對(duì)它們加以區(qū)分以防止覆蓋
		title = title + str(i)
		i = i + 1
	return title


def download(folder, picurl, title, headers): # 將圖片下載到文件夾中
	img = requests.get(picurl, headers=headers, proxies=proxies)
	if img.status_code == 200:
		with open(folder + '\\' + title + '.jpg', 'wb') as file: # 保存圖片
			print("downloading:" + title)
			file.write(img.content)
	else:
		print("download pictures error!")


def main():
	global i
	id = input('input the id of the artist:')
	cookie = input('input your cookie:') # 半自動(dòng)爬蟲,需要自己事先登錄pixiv以獲取cookie
	folder = makefolder(id)
	IDlist = getAuthorAllPicID(id, cookie)
	getPictures(folder, IDlist, cookie)


if __name__ == '__main__':
	main()