基于python爬虫的豆瓣自动回复.

最新的豆瓣自动回复
废话不多说 直接挂代码.

import requests
import re
import time
#from chaojiying import *
from random import choice , randint

ran = [.....自动回复的内容]
# 用于维持登录会话，requests高级用法
s = requests.Session ()

headers = {
	'Host': 'www.douban.com' ,
	'User-Agent': 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'
}

# 登录
def login():
	headers = {
		'User-Agent': 'Mozilla/5.0 (Linux; Android 4.4.2; Nexus 4 Build/KOT49H) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.114 Mobile Safari/537.36'
	}
	url = 'https://accounts.douban.com/j/mobile/login/basic'
	data = {
		'ck': '' ,
		'name': '豆瓣账号' ,
		'password': '豆瓣密码' ,
		'remember': 'false' ,
		'ticket': '' ,
	}
	html = s.post (url , headers=headers , data=data)
	if html.json ()['status'] == 'success':
		print ('登录成功')
	print (html.cookies.get_dict ())
	return html.cookies.get_dict ()

# 获取个人信息
def get_user_data():
	groups_url = 'https://www.douban.com/group/people/' + cookies['dbcl2'].split (':')[0][1:] + '/joins'
	html = s.get (groups_url , headers=headers).text
	
	r = re.compile (r'<a href=".*?&ck=(.*?)".*?</a>' , re.S)
	ck = re.findall (r , html)[0]  # 获取ck值
	
	r = re.compile (r'<a title=.*?href="(.*?)".*?</a>' , re.S)
	groups = re.findall (r , html)
	print (ck)
	return groups , ck

# 获取各个组的最新讨论并自动回复.
def parase_groups(group , m):
	print(1)
	headers = {
		'Connection': 'keep-alive' ,
		'Host': 'www.douban.com' ,
		'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
	}
	html = s.get (group + 'discussion?start='+m , headers=headers).text
	r = re.compile (r'<td class="title">.*?<a href="(.*?)".*?title=.*?<td.*?<td nowrap="nowrap" class="">(.*?)</td>', re.S)
	result = re.findall (r , html)
	url_test =[url[0] for url in result]
	talks_url = []
	comments = [comment[1] for comment in result]
	
	for i in range(len(comments)):
		if comments[i]:
			if int(comments[i]) <=5:
				talks_url.append(url_test[i])
		else:
			talks_url.append(url_test[i])
			
	
	if  talks_url:
		for url in talks_url:
			print (url)
			headers = {
				'Host': 'www.douban.com' ,
				'Referer': group + 'discussion?start=0' ,
				'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.122 Safari/537.36'
			}
			html = s.get (url , headers=headers).text
		
			r = re.compile (r'<a href=".*?&ck=(.*?)".*?</a>' , re.S)
			ck = re.findall (r , html)[0]  # 获取ck值
			
			r = re.compile (r'captcha.*?src="(.*?)"')
			pic = re.findall (r , html)
			url = url + 'add_comment#last'
			
			param = {
				'ck': ck ,
				'rv_comment': choice (ran) ,
			}
			print ('评论了:%s' % param['rv_comment'])
			if pic:
				param['captcha-id'] = re.findall ('id=(.*?)&' , pic[0])[0]
				print ('有验证码\n验证码')
				with open (pic[0][0] + '.jpg' , 'wb') as f:
					f.write (requests.get (pic[0] , headers=headers).content)
					print ("%s下载完成" % pic)
				
				#chaojiying = Chaojiying_Client ('dbyejd' , 'dbyejd2020..' ,
				                                '37f81b4542a8cd3cf9eb96071d65a0e2')  # 用户中心>>软件ID 生成一个替换 96001
				#im = open (pic[0][0] + '.jpg' , 'rb').read ()  # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
				#param['captcha-solution'] = chaojiying.PostPic (im , 1902)['pic_str']
				#print (param['captcha-solution'] , param['captcha-id'])
				try:
					response = s.post (url , headers=headers , data=param , timeout=5)
					print (response.status_code)
					if int (response.status_code) == 403:
						print (time.asctime ())
				except:
					print ('发言失败.')
		
			else:
				print ('无验证码')
				try:
					response = s.post (url , headers=headers , data=param , timeout=5)
					print (response.status_code)
					if int (response.status_code) == 403:
						print (time.asctime ())
			
				except:
					print ('发言失败.')
		
			time.sleep (randint (10 , 30))
if __name__ == '__main__':
	cookies = login ()
	groups , ck = get_user_data ()
	time.sleep (2)
	while True:
		for group in groups:
			for m in ('0','25','50'):
				parase_groups (group , m)
				time.sleep (20)

有需要定制爬虫,定制自动回复.联系q:940755193