import requests

import json

from tqdm import tqdm

import datetime

import time

import random

import csv

​

# 一条主微博链接部分评论, 需要构造参数max_id获取全部ajax

up_main_url = 'https://m.weibo.cn/comments/hotflow?id=4596226979532970&mid=4596226979532970&max_id_type=0'

headers = {

# ua代理

'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.141 Safari/537.36 Edg/87.0.664.75',

# 登录信息

'cookie': 'SINAGLOBAL=5702871423690.898.1595515471453; SCF=Ah2tNvhR8eWX01S-DmF8uwYWORUbgfA0U3GnciJplYvqE1sn2zJtPdkJ9ork9dAVV8G7m-9kbF-PwIHsf3jHsUw.; SUB=_2A25NDifYDeRhGeBK7lYS9ifFwjSIHXVu8UmQrDV8PUJbkNANLRmlkW1NR7rne18NXZNqVxsfD3DngazoVlT-Fvpf; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WhhI1TcfcjnxZJInnV-kd405NHD95QcSh-Xe0q41K.RWs4DqcjQi--ciK.RiKLsi--Ni-24i-iWi--Xi-z4iKyFi--fi-2XiKLhSKeEeBtt; wvr=6; _s_tentry=www.sogou.com; UOR=,,www.sogou.com; Apache=9073188868783.379.1611369496580; ULV=1611369496594:3:3:3:9073188868783.379.1611369496580:1611281802597; webim_unReadCount=%7B%22time%22%3A1611369649613%2C%22dm_pub_total%22%3A0%2C%22chat_group_client%22%3A0%2C%22chat_group_notice%22%3A0%2C%22allcountNum%22%3A63%2C%22msgbox%22%3A0%7D'

}

response = requests.get(url=up_main_url, headers=headers)

if response.status_code == 200:

text = response.text.encode("gbk", "ignore").decode("gbk", "ignore") # 解决报错双重严格限制

content = json.loads(text) # 将文本转为json格式

try:

data = content['data']['data'] # 获取评论列表

for comment in tqdm(data, desc='花花评论爬取加载进度--->!'):

time.sleep(random.random())

text = str(comment['text']) # 获取文本信息

# 卧槽，我房子又塌了

# 处理文本信息,find函数找到

if text.find('

text = text[:text.find('

create_time = comment['created_at'] # 发布时间

# 格林威治时间格式字符串 Wed Jul 10 20:00:09 +0800 2019 转换为好理解的标准时间格式 2019-07-10 20:00:09

# Fri Jan 22 17:56:48 +0800 2021 转换为标准时间格式 2021/1/22 17:56:48

std_transfer = '%a %b %d %H:%M:%S %z %Y' # 转换的一个格式

std_create_time = datetime.datetime.strptime(create_time, std_transfer)

user_name = comment['user']["screen_name"] # 用户姓名

user_id = comment['user']['id'] # 用户id

user_followers_count = comment['user']['followers_count'] # 该用户粉丝数

user_follow_count = comment['user']['follow_count'] # 该用户关注数

user_gender = comment['user']['gender'] # 用户性别

total_number = comment["total_number"] # 总回复数

like_count = comment["like_count"] # 点赞数

flag_id = comment["id"] # 二级评论url构造所需id

print('')

# print(f'内容: {text}')

# print(f'用户名: {user_name}')

# print(f'评论时间: {std_create_time}')

# print(f'id：{user_id}')

# print(f'关注人数: {user_follow_count}')

# print(f'粉丝: {user_followers_count}')

# print(f'性别: {user_gender}')

# print(f'回复数量: {total_number}')

# print(f'点赞数: {like_count}')

# print(f'cid: {flag_id}')

#print('成功保存信息!')

except:

print("啊这，今晚是上分局!被反爬了")

pass