#!/usr/bin/env python3

# -*- coding: utf-8 -*-

import time

import re

import requests

import urllib3

# 禁用requests提交https的get请求时的报错

urllib3.disable_warnings()

'''根据page_num号，获取发出的评论页html'''

def get_comment_html(page_num):

header = {'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8','Accept-Encoding':'gzip, deflate, br','Accept-Language':'zh-CN,zh;q=0.9','Connection':'keep-alive','DNT':'1','Host':'weibo.com','Upgrade-Insecure-Requests':'1','User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.94 Safari/537.36','Cookie':r''}

comment_url = 'https://weibo.com/comment/outbox?page=' + str(page_num)

comment_response = requests.get(comment_url, headers=header, verify=False)

return comment_response.text

'''根据评论页html，获取评论comment_id_list'''

def get_comment_id_list(comment_html):

comment_id_list = []

pairs = re.findall(r'comment_id=\d{16}', comment_html)

for pair in pairs:

comment_id_list.append(pair.split('=')[-1])

return comment_id_list

'''根据comment_id删除该条评论'''

def del_comment(cid):

headers = {'Host':'weibo.com','Connection':'keep-alive','Origin':'https://weibo.com','X-Requested-With':'XMLHttpRequest','User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML:like Gecko) Chrome/62.0.3202.94 Safari/537.36','Accept':'*/*','DNT':'1','Referer':'https://weibo.com/comment/outbox?page=1','Accept-Language':'zh-CN,zh;q=0.9','Accept-Encoding':'gzip:deflate','Content-Type':'application/x-www-form-urlencoded','Content-Length':'25','Cookie':r''}

delete_comment_url = 'https://weibo.com/aj/comment/del?ajwvr=6&__rnd='

time_stamp = int(time.time()) * 1000

# url中包含时间戳(毫秒)

delete_comment_url = delete_comment_url + str(time_stamp)

body = {'cid':cid, '_t':'0'}

delete_comment_response = requests.post(delete_comment_url, data=body, headers=headers, verify=False)

print(delete_comment_response.text)

'''获取当前用户共有多少评论分页'''

def get_comment_page_end_num():

comment_html = get_comment_html(1)

pairs = re.findall(r'\\t(\d+)', comment_html)

return int(pairs[-1:][0])

if __name__ == '__main__':

while True:

count = 0

start_page_num = 1

end_page_num = get_comment_page_end_num()

for page_num in range(start_page_num, end_page_num):

comment_html = get_comment_html(page_num)

print('获得%d页评论，评论页大小%d' % (page_num, len(comment_html)))

comment_id_list = get_comment_id_list(comment_html)

if len(comment_id_list) == 0:

time.sleep(2)

continue

for comment_id in comment_id_list:

del_comment(comment_id)

count += 1

time.sleep(5)

if count == 0:

break