import  requestsimport  jsonfrom bs4 import BeautifulSoupfrom    urllib.request import urlretrieve#构造函数def sk():    #请求头    header={        'user-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.89 Safari/537.36',        'cookie':'SINAGLOBAL=7539808571181.766.1594904938878; login_sid_t=d5cd1bd9f275813e62c15325ed13f107; cross_origin_proto=SSL; _s_tentry=www.google.com.hk; Apache=6567219473432.515.1594948744234; ULV=1594948744243:2:2:2:6567219473432.515.1594948744234:1594904938884; UOR=www.google.com.hk,www.weibo.com,www.google.com.hk; SUB=_2A25yFI6zDeRhGeBG4lAS-CvEzDWIHXVRY-d7rDV8PUNbmtANLWvCkW9NQfFYtiChpvR5j8HL-b3qtR4iP5VWlahr; SUBP=0033WrSXqPxfM725Ws9jqgMF55529P9D9WFgGcLsqLAolPfV0X13gOKE5JpX5KzhUgL.FoqR1Kz01h-RS0.2dJLoIc2LxKqL1hnL1K2LxKML1KBLBKyydCH8SFHFxFHWeFH8SE-4SFHW1s8E9CH8SFHF1FHW1sL0i--Ri-isiKL8i--NiKL2iKn7i--Xi-iFiK.ci--fi-2fi-z4i--fi-88iKn0; SUHB=079jhOx3o5wTZ7; ALF=1626485347; SSOLoginState=1594949347; wvr=6; WBStorage=42212210b087ca50|undefined; webim_unReadCount={"time":1594950237072,"dm_pub_total":0,"chat_group_client":0,"chat_group_notice":0,"allcountNum":0,"msgbox":0}'    }    #循环    for z in range(1,9):#页数        url ='https://photo.weibo.com/photos/get_all?uid=6179279336&album_id=4088933483139641&count=30&page='+str(z)+'&type=3&__rnd=1594950245139'        s=requests.get(url,headers=header)        t=s.json()['data']['photo_list']        for x in t:            name =x['pic_name']            src='https://wx2.sinaimg.cn/mw690/'+name #不一样的名字            #下载函数            download(name,src,z)def download(name,src,z):    try:        path =r'G:/Desktop/blog/'#保存路径        urlretrieve(src,path+name)        print('——————下载第'+str(z)+'页————————')    except Exception as e:        print('_______')if __name__ =='__main__':    sk()

# -*- coding: utf-8 -*-
import urllib.request
import json
import requests
import os
 
path = 'D:\\weibo'
 
#id = '[url=tel:2093492691]2093492691[/url]'这里决定爬取人的ID
id = '[url=tel:6049590367]6049590367[/url]'
proxy_addr = "122.241.72.191:808"
pic_num = 0
weibo_name = "programmer"
 
 
def use_proxy(url, proxy_addr):
    req = urllib.request.Request(url)
    req.add_header("User-Agent",
                   "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.221 Safari/537.36 SE 2.X MetaSr 1.0")
    proxy = urllib.request.ProxyHandler({'http': proxy_addr})
    opener = urllib.request.build_opener(proxy, urllib.request.HTTPHandler)
    urllib.request.install_opener(opener)
    data = urllib.request.urlopen(req).read().decode('utf-8', 'ignore')
    return data
 
 
def get_containerid(url):
    data = use_proxy(url, proxy_addr)
    content = json.loads(data).get('data')
    for data in content.get('tabsInfo').get('tabs'):
        if (data.get('tab_type') == 'weibo'):
            containerid = data.get('containerid')
    return containerid
 
 
def get_userInfo(id):
    url = 'https://m.weibo.cn/api/container/getIndex?type=uid&value=' + id
    data = use_proxy(url, proxy_addr)
    content = json.loads(data).get('data')
    profile_image_url = content.get('userInfo').get('profile_image_url')
    description = content.get('userInfo').get('description')
    profile_url = content.get('userInfo').get('profile_url')
    verified = content.get('userInfo').get('verified')
    guanzhu = content.get('userInfo').get('follow_count')
    name = content.get('userInfo').get('screen_name')
    fensi = content.get('userInfo').get('followers_count')
    gender = content.get('userInfo').get('gender')
    urank = content.get('userInfo').get('urank')
    print("微博昵称：" + name + "\n" + "微博主页地址：" + profile_url + "\n" + "微博头像地址：" + profile_image_url + "\n" + "是否认证：" + str(
        verified) + "\n" + "微博说明：" + description + "\n" + "关注人数：" + str(guanzhu) + "\n" + "粉丝数：" + str(
        fensi) + "\n" + "性别：" + gender + "\n" + "微博等级：" + str(urank) + "\n")
 
 
def get_weibo(id, file):
    global pic_num
    i = 1
    while True:
        url = 'https://m.weibo.cn/api/container/getIndex?type=uid&value=' + id
        weibo_url = 'https://m.weibo.cn/api/container/getIndex?type=uid&value=' + id + '&containerid=' + get_containerid(
            url) + '&page=' + str(i)
        try:
            data = use_proxy(weibo_url, proxy_addr)
            content = json.loads(data).get('data')
            cards = content.get('cards')
            if (len(cards) > 0):
                for j in range(len(cards)):
                    print("-----正在爬取第" + str(i) + "页，第" + str(j) + "条微博------")
                    card_type = cards[j].get('card_type')
                    if (card_type == 9):
                        mblog = cards[j].get('mblog')
                        attitudes_count = mblog.get('attitudes_count')
                        comments_count = mblog.get('comments_count')
                        created_at = mblog.get('created_at')
                        reposts_count = mblog.get('reposts_count')
                        scheme = cards[j].get('scheme')
                        text = mblog.get('text')
                        if mblog.get('pics') != None:
                            # print(mblog.get('original_pic'))
                            # print(mblog.get('pics'))
                            pic_archive = mblog.get('pics')
                            for _ in range(len(pic_archive)):
                                pic_num += 1
                                print(pic_archive[_]['large']['url'])
                                imgurl = pic_archive[_]['large']['url']
                                img = requests.get(imgurl)
                                f = open(path + weibo_name + '\\' + str(pic_num) + str(imgurl[-4:]),
                                         'ab')  # 存储图片，多媒体文件需要参数b（二进制文件）
                                f.write(img.content)  # 多媒体存储content
                                f.close()
 
                        with open(file, 'a', encoding='utf-8') as fh:
                            fh.write("----第" + str(i) + "页，第" + str(j) + "条微博----" + "\n")
                            fh.write("微博地址：" + str(scheme) + "\n" + "发布时间：" + str(
                                created_at) + "\n" + "微博内容：" + text + "\n" + "点赞数：" + str(
                                attitudes_count) + "\n" + "评论数：" + str(comments_count) + "\n" + "转发数：" + str(
                                reposts_count) + "\n")
                i += 1
            else:
                break
        except Exception as e:
            print(e)
            pass
 
 
if __name__ == "__main__":
    if os.path.isdir(path + weibo_name):
        pass
    else:
        os.mkdir(path + weibo_name)
    file = path + weibo_name + '\\' + weibo_name + ".txt"
    get_userInfo(id)
    get_weibo(id, file)