p站自动收藏画作 post请求，request payload

本篇内容可以和上一篇结合使用p站爬取数据绕过vip筛选高人气画作
先放码

import requests
import json
import time
from requests.packages.urllib3.exceptions import InsecureRequestWarning
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)

def load_cookies():
	cookie_json = {}
	try:
		with open('cookies.json','r',encoding = 'utf-8') as cookies_file:
			cookie = json.load(cookies_file)
	except:
		print('cookies读取失败')
	else:
		for i in range(len(cookie)):
			if cookie[i]['domain'] == '.pixiv.net':
				cookie_json[cookie[i]['name']] = cookie[i]['value']
		return cookie_json

def get_session(item_id):
	head = {
	'accept': 'application/json',
	'Accept-Encoding': 'gzip, deflate, br',
	'Accept-Language': 'zh-CN,zh;q=0.9',
	'Connection': 'keep-alive',
	'Content-Length': '60',
	'content-type': 'application/json; charset=utf-8',
	'Host': 'www.pixiv.net',
	'Origin': 'https://www.pixiv.net',
	'Referer': 'https://www.pixiv.net/users/'+item_id+'/bookmarks/artworks',
	'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400',
	'x-csrf-token': '584507416fc0fc3c61bdb59f7b7a0792',
	}
	
	cookie_json = load_cookies()
	
	session = requests.session()

	session.headers = head
	requests.utils.add_dict_to_cookiejar(session.cookies,cookie_json)

	return session

def Collection(item_id):
	session = get_session(item_id)
	request_payload = {"illust_id":item_id,"restrict":0,"comment":"","tags":[]}
	url = 'https://www.pixiv.net/ajax/illusts/bookmarks/add'
	try:
		Collection = session.post(url,data=json.dumps(request_payload),verify=False).json()
	except:
		print('错误:'+str(item_id))
	else:
		if Collection['error'] == False:
			print('保存成功:'+str(item_id))
		else:
			print(Collection)


def data_load(folder):
	try:
		Collection_id = json.load(open('Collection.json','r',encoding = 'utf-8'))
	except:
		Collection_id = []
	data = json.load(open('./item_data/'+folder+'.json','r',encoding = 'utf-8'))
	for item_id in data:
		if int(data[item_id]['book_mark_count']) >= 40000 or int(data[item_id]['book_like_count']) >= 20000:
			if item_id in Collection_id:
				pass
			else:
				Collection(item_id)
				Collection_id.append(item_id)
				json.dump(Collection_id,open('Collection.json','w',encoding = 'utf-8'))
				time.sleep(2)


if __name__ == '__main__':
	data_load('2020-03-28-22')

load_cookies()

由于是关于收藏夹的改动，肯定需要验证登入啊
这就不加以赘述了，详情请看p站收藏夹爬虫

get_session(item_id)

def get_session(item_id):
	head = {
	'accept': 'application/json',
	'Accept-Encoding': 'gzip, deflate, br',
	'Accept-Language': 'zh-CN,zh;q=0.9',
	'Connection': 'keep-alive',
	'Content-Length': '60',
	'content-type': 'application/json; charset=utf-8',
	'Host': 'www.pixiv.net',
	'Origin': 'https://www.pixiv.net',
	'Referer': 'https://www.pixiv.net/users/'+item_id+'/bookmarks/artworks',
	'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400',
	'x-csrf-token': '',  #该参数在请求中找
	}
	
	cookie_json = load_cookies()
	
	session = requests.session()

	session.headers = head
	requests.utils.add_dict_to_cookiejar(session.cookies,cookie_json)

	return session

大家注意到请求头中存在x-csrf-token，这个每个人的值都不同。需要到网页中查看
先点开任意一个图片项目，如何在打开F12的情况下


这些参数必不可少，还有referer的配置，需要根据套图id的变化而变化。

Collection(item_id)

def Collection(item_id):
	session = get_session(item_id)
	request_payload = {"illust_id":item_id,"restrict":0,"comment":"","tags":[]}
	url = 'https://www.pixiv.net/ajax/illusts/bookmarks/add'
	try:
		Collection = session.post(url,data=json.dumps(request_payload),verify=False).json()
	except:
		print('错误:'+str(item_id))
	else:
		if Collection['error'] == False:
			print('保存成功:'+str(item_id))
		else:
			print(Collection)

唯一需要变动的是illust_id的值。这里要使用post方法传入数据。

data_load(folder)

def data_load(folder):
	try:
		Collection_id = json.load(open('Collection.json','r',encoding = 'utf-8'))
	except:
		Collection_id = []
	data = json.load(open('./item_data/'+folder+'.json','r',encoding = 'utf-8'))
	for item_id in data:
		if int(data[item_id]['book_mark_count']) >= 40000 or int(data[item_id]['book_like_count']) >= 20000:
			#print('一档   '+'https://www.pixiv.net/artworks/'+item_id+'   '+data[item_id]['book_title'])
			if item_id in Collection_id:
				pass
			else:
				Collection(item_id)
				Collection_id.append(item_id)
				json.dump(Collection_id,open('Collection.json','w',encoding = 'utf-8'))
				time.sleep(2)
		elif 40000 > int(data[item_id]['book_mark_count']) >= 30000 or 20000 > int(data[item_id]['book_like_count']) >= 17500:
			#print('二档   '+'https://www.pixiv.net/artworks/'+item_id+'   '+data[item_id]['book_title'])
			if item_id in Collection_id:
				pass
			else:
				Collection(item_id)
				Collection_id.append(item_id)
				json.dump(Collection_id,open('Collection.json','w',encoding = 'utf-8'))
				time.sleep(2)

首先获取在上篇文章中讲述的方法保存的数据，再通过筛选，获取到高人气的画作。
在通过Collection()方法进行收藏。为了减少重复工作，我加入了一条关于验证的代码

def data_load(folder):
	try:
		Collection_id = json.load(open('Collection.json','r',encoding = 'utf-8'))
	except:
		Collection_id = []
				...snip...
			if item_id in Collection_id:
				pass
			else:
				Collection(item_id)
				Collection_id.append(item_id)
				json.dump(Collection_id,open('Collection.json','w',encoding = 'utf-8'))
				time.sleep(2)

每次收藏时记录已保存的套图id，如果已经收藏过就跳过

时间：2020/3/29