spider/weibo/main.py

import hashlib
import math
import time
import zlib

import requests
import re
import json


class Wb:
    def __init__(self, cookie):
        self.chunk_size = 1024 * 1024 * 8
        self.xsrf_token = None
        if "XSRF-TOKEN" in cookie:
            del cookie["XSRF-TOKEN"]
        if "xsrf-token" in cookie:
            del cookie["xsrf-token"]
        self.cookie = cookie
        self.headers = self.get_headers()
        self.screen_name, self.idstr, self.xsrf_token = self.get_tk_info()
        self.headers['x-xsrf-token'] = self.xsrf_token
        self.cookie["XSRF-TOKEN"] = self.xsrf_token

        # self.headers['']

    def md5(self, data):
        if type(data) == str:
            data = data.encode("utf-8")
        return hashlib.md5(data).hexdigest()

    def get_cs(self, data):
        return zlib.crc32(data) & 0xffffffff

    def get_session_id(self, video_data, vide_path):
        data = f'{str(int(time.time() * 1000))}|{len(video_data)}|{vide_path}|video|{str(int(time.time()))}'
        return hashlib.md5(data.encode()).hexdigest()

    def get_headers(self):
        headers = {
            "cache-control": "no-cache",
            "pragma": "no-cache",
            "priority": "u=0, i",
            "sec-ch-ua": "\"Chromium\";v=\"9\", \"Not?A_Brand\";v=\"8\"",
            "sec-ch-ua-mobile": "?0",
            "sec-ch-ua-platform": "\"Windows\"",
            "sec-fetch-dest": "document",
            "sec-fetch-mode": "navigate",
            "sec-fetch-site": "same-origin",
            "sec-fetch-user": "?1",
            "upgrade-insecure-requests": "1",
            "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36 SLBrowser/9.0.6.8151 SLBChan/10 SLBVPV/64-bit"
        }
        if self.xsrf_token:
            headers['x-xsrf-token'] = self.xsrf_token
        return headers

    def get_tk_info(self):
        url = "https://weibo.com/"
        response = requests.get(url, headers=self.headers, cookies=self.cookie)
        data = json.loads(re.search('window\.\$CONFIG = (.*?);}', response.text).group(1))
        user = data['user']
        screen_name = user['screen_name']
        idstr = user['idstr']
        xsrf_token = response.cookies.get('XSRF-TOKEN')
        print(screen_name, idstr, xsrf_token)
        return screen_name, idstr, xsrf_token

    def put_image(self, image_data):
        url = 'https://picupload.weibo.com/interface/upload.php?'
        params = {
            "file_source": "1",
            "cs": self.get_cs(image_data),
            "ent": "miniblog",
            "appid": "339644097",
            "uid": self.idstr,
            "raw_md5": self.md5(image_data),
            "ori": "1",
            "mpos": "1",
            "nick": self.screen_name,
            "pri": "0",
            "request_id": str(int(time.time() * 1000)),
            "file_size": len(image_data)
        }
        res = requests.post(url=url, data=image_data, headers=self.headers, cookies=self.cookie, params=params).json()
        print(res)
        return res

    def get_media_group_id(self):
        url = "https://weibo.com/ajax/multimedia/mediaGroupInit"
        headers = self.get_headers()
        headers.update(
            {
                "referer": "https://weibo.com/",
                "sec-fetch-dest": "empty",
                "sec-fetch-mode": "cors",
                "sec-fetch-site": "same-origin",
                "server-version": "v2026.03.04.2",
            }
        )
        response = requests.get(url, headers=headers, cookies=self.cookie).json()
        print(response)
        return response['data']['media_group_id']

    def ini_video_id(self, media_group_id, video_name, video_data):
        url = "https://fileplatform-cn1.api.weibo.com/2/fileplatform/init.json"

        params = {
            "source": "339644097",
            "size": len(video_data),
            "name": video_name,
            "type": "video",
            "client": "web",
            "session_id": self.get_session_id(video_data, video_name)
        }

        boundary = f"2067456weiboPro{str(int(time.time()))}"

        headers = self.get_headers()
        headers.update({

            "Content-Type": f"multipart/mixed; boundary={boundary}",

        })

        # 完全按 curl 构造原始 multipart body
        body = (
                f"--{boundary}\r\n"
                'Content-Disposition: form-data; name="biz_file"\r\n\r\n'
                '{"mediaprops":"{\\"screenshot\\":1,\\"media_group_id\\":\\"' + media_group_id + '\\"}"}\r\n'
                                                                                                 f"--{boundary}--\r\n"
        )

        response = requests.post(
            url,
            params=params,
            headers=headers,
            cookies=cookies,
            data=body.encode("utf-8")
        )
        print(response.json())
        return response.json()

    def upload_video(self, upload_id, media_id, video_data, index, chunk_count, start_loc):
        url = "https://up-cn1.video.weibocdn.com/2/fileplatform/upload.json?"
        params = {
            "source": "339644097",
            "upload_id": upload_id,
            "media_id": media_id,
            "upload_protocol": "binary",
            "type": "video",
            "client": "web",
            "check": self.md5(video_data),
            "index": index,
            "size": len(video_data),
            "start_loc": start_loc,
            "count": chunk_count
        }
        # print(params)
        res = requests.post(url=url, params=params, headers=self.headers, cookies=cookies, data=video_data
                            ).json()
        print(res)
        return res

    def chak_video(self, upload_id, media_id, size, count):
        url = "https://fileplatform-cn1.api.weibo.com/2/fileplatform/check.json"
        data = {
            "source": "339644097",
            "upload_id": upload_id,
            "media_id": media_id,
            "upload_protocol": "binary",
            "count": count,
            "action": "finish",
            "size": size,
            "client": "web",
            "status": ""
        }
        response = requests.post(url, headers=self.headers, cookies=cookies, data=data).json()
        print(response)
        return response

    def get_video_pid(self, media_id):
        url = "https://weibo.com/ajax/multimedia/output"
        params = {
            "source": "339644097",
            "ids": media_id,
            "labels": "screenshot"
        }
        headers = self.get_headers()
        headers.update({

            "referer": "https://weibo.com/",

        })
        for i in range(10):
            response = requests.get(url, headers=headers, cookies=cookies, params=params).json()
            print(response)
            if response['data'] == {}:
                time.sleep(5)
                continue
            else:
                return json.loads(response['data'][str(media_id)]['screenshot']['file_detail'])['files'][0]['file_id']
        return False

    def release(self, pic_id, content):
        url = "https://weibo.com/ajax/statuses/update"
        data = {
            "content": content,
            "visible": "0",
            "share_id": "",
            "vote": "",
            "media": "",
            "need_transcode": "1",
            "pic_id": json.dumps(pic_id, ensure_ascii=False)
        }

        headers = self.get_headers()
        headers.update({

            "origin": "https://weibo.com",
            "pragma": "no-cache",
            "priority": "u=1, i",
            "referer": "https://weibo.com/",
            "sec-ch-ua": "\"Chromium\";v=\"9\", \"Not?A_Brand\";v=\"8\"",
            "sec-ch-ua-mobile": "?0",
            "sec-ch-ua-platform": "\"Windows\"",
            "sec-fetch-dest": "empty",
            "sec-fetch-mode": "cors",
            "sec-fetch-site": "same-origin",
            "server-version": "v2026.03.04.2",

        }
        )

        response = requests.post(url, headers=headers, cookies=self.cookie, data=data).text
        print(response)
        return response

    def run_video(self, video_name):
        media_group_id = self.get_media_group_id()
        with open(video_name, "rb") as f:
            video_data = f.read()
            video_info = self.ini_video_id(media_group_id=media_group_id, video_name=video_name, video_data=video_data)
            upload_id = video_info["upload_id"]
            media_id = video_info["media_id"]
            chunk_count = math.ceil(len(video_data) / self.chunk_size)
            for index in range(chunk_count):
                # start = index * self.chunk_size
                # end = min((index + 1) * self.chunk_size, len(video_data))
                # f.seek(start)
                # chunk_data = f.read(end - start)
                # print(start, end)
                # self.upload_video(upload_id=upload_id, media_id=media_id, video_data=chunk_data, index=index,
                #                   chunk_count=chunk_count, start_loc=start)
                start = index * self.chunk_size
                end = min(start + self.chunk_size, len(video_data))
                f.seek(start)
                chunk_data = f.read(end - start)

                self.upload_video(
                    upload_id=upload_id,
                    media_id=media_id,
                    video_data=chunk_data,
                    index=index,
                    chunk_count=chunk_count,
                    start_loc=start
                )
            self.chak_video(upload_id=upload_id, media_id=media_id, size=len(video_data), count=chunk_count)
        res = {
            "type": "video",
            "media_id": media_id,
            "media_group_id": media_group_id
        }

        pid = self.get_video_pid(media_id)
        if pid:
            res['pid'] = pid
        return res

    def run_images(self, image_path):
        with open(image_path, 'rb') as f:
            pid = self.put_image(image_data=f.read())['pic']['pid']
            return {
                "type": "image/png",
                "pid": pid
            }

    def run(self):
        pid_list = []
        pid_list.append(self.run_images(r'D:\2026-3\image\2.png'))
        pid_list.append(self.run_video(r'1.mp4'))
        print(pid_list)
        self.release(pic_id=pid_list, content='你们好我是2222')


if __name__ == '__main__':
    cookies = {
        "SCF": "AnPzE03xm8BB9HlgIFL6amrpHcKurEbxl_Lidx2mwHySmzyyoCMjVNxfKQCNBwYxr-gvT8-50DlpsHI_XJIJlqA.",
        "SUB": "_2A25EosHEDeRhGeFG7lYX9SnKzT2IHXVn3lsMrDV8PUNbmtAbLRnGkW1NeV0u11k3Ss6dRbldGFr1JUHhVsbep0_3",
        "SUBP": "0033WrSXqPxfM725Ws9jqgMF55529P9D9W5mUlS3fLogK2SEkeFqLNEa5NHD95QN1h-XSo-NSoqpWs4DqcjMi--NiK.Xi-2Ri--ciKnRi-zNS0nfShqfS0qceBtt",
        "ALF": "02_1775124116",
        "SINAGLOBAL": "8767812016817.392.1772592155581",
        "ULV": "1772610236625:2:2:2:6590739668820.657.1772610236578:1772592155651",
        "XSRF-TOKEN": "DQZxABOM_NfYDlXz1lTy1cOD",
        "WBPSESS": "uH_pEmgfiICupYDn2MNJGBnQEfhqzo2bMY0VUuWK05-TR78aeKUmP0AyDqfzYmdbsI2dVYBedhIHV1snwDUpD1Lz1KXhMSCgjztzOlrwCTDLIhXWNZMTlGNIkU-lI5cmUf2721Pj2oQsCiRB-HQg1w=="
    }
    # Wb(cookies).get_video_pid('5272880565649510')
    # print(Wb(cookies).run_video(video_name='1.mp4'))
    # print(Wb(cookies).run_images(r'D:\2026-3\image\2.png'))
    print(Wb(cookies).run())
    # Wb(cookies).release([{'type': 'image/png', 'pid': '008zzlgNgy1iavb8voqu5j30cu03iaa7'},
    #                      {'type': 'video', 'media_id': '5272882008227937',
    #                       'media_group_id': '0c22cd44-17db-11f1-b886-09e635c8dab8'}],
    #                     '你们好')