首页 > 教程

今天给大家分享闲鱼的数据获取和逆向，只需要在终端输入想搜索的物品名，再输入想下载内容的页码，
对应数据的csv文件便会自动命名好并创建在相应的文件夹内，以供大家观看和相应需求。
值得注意的是cookies 过很长一段时间会失效，到时候则需要大家手动替换这一栏啦，也不是很难。

from hashlib import md5
import time
import requests
import csv
import os
 
from pathlib import Path
 
# 定义路径
os_path = Path.cwd() / '闲鱼'
print(os_path)
# 检查目录是否存在，如果不存在则创建
if not os_path.exists():
    os_path.mkdir(parents=True, exist_ok=True)  # parents=True 支持多级目录创建
 
 
 
 
cookies = {
    'cna': 'o2VyIG74FTMCASShMKcIxy+k',
    'cookie2': '124e5ba3daf492b75775ddeb501c4470',
    '_samesite_flag_': 'true',
    't': 'af37bded5c848ba4245c9527b710787f',
    '_tb_token_': 'e33ff5759af39',
    'mtop_partitioned_detect': '1',
    '_m_h5_tk': '43a8d19ad104ac584f86e23e273c6aa8_1743764419015',
    '_m_h5_tk_enc': '37d8a137028ac2a98bb85db99720098f',
    'xlly_s': '1',
}   #cookies过一段时间会刷新，记得改成自己电脑的cookies，
headers = {
 
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/134.0.0.0 Safari/537.36 Edg/134.0.0.0',
    # 'cookie': 'cna=o2VyIG74FTMCASShMKcIxy+k; cookie2=124e5ba3daf492b75775ddeb501c4470; xlly_s=1; _samesite_flag_=true; t=af37bded5c848ba4245c9527b710787f; _tb_token_=e33ff5759af39; mtop_partitioned_detect=1; _m_h5_tk=179c6ebaaf128f51c3115d032879d73e_1743696440707; _m_h5_tk_enc=e52128cad70c5425624fe37abe435555; tfstk=ggljBubsPijXYqIoonLzPgrFhmFsCcOF5Nat-VCVWSFAXG3L4mr4gFA_Xmqrgou4MlCsbVlqbfgG1P3tjEqwoLumo5V9YHR6Tq00ME3tRjwYw_UIyPI9U-IeCSJJYHReaKQ81ntE02oQCLag2rUTB5L5ePzg6rFO6UZ85yXODcF9PUaTSsCAMrERwy4T6lnT6Ug8qPMEwQay7ogXkrjvDARFBqZ561h7yhqKlw5Qub4jHk3xG1fMJrwbvqEWxbU2383gCfbG1o3xKc4KDiKUnVHSVrN6atFKPAnQrjdFczDqy2r-RwCKoSMIOSHXqTVqcbF-Mv_O64Nbm8U7Fit7vj0-t7ey9eg-ZmumNV796zoU2qcY1BL3GSEYNzcwqsEseAh4n5jvY-0tF0ab9gP5TkZm3O_7K1a7YUT5IOj2Atuy2k1qP-UuzM8WPiN8Hz47YUT5IO2Yrz8ePUsbw',
}
 
keyword=input("请输入搜索物品：")
page=input("请输入搜索页码：")
data = {
    'data': f'{{"pageNumber":"{page}","keyword": "{keyword}","fromFilter":false,"rowsPerPage":30,"sortValue":"","sortField":"","customDistance":"","gps":"","propValueStr":{{}},"customGps":"","searchReqFromPage":"pcSearch","extraFilterValue":"{{}}","userPositionJson":"{{}}"}}'
}
 
time = str(round(time.time() * 1000))
params = {
    'jsv': '2.7.2',
    'appKey': '34839810',
    't': time,
    'v': '1.0',
    'type': 'originaljson',
    'accountSite': 'xianyu',
    'dataType': 'json',
    'timeout': '20000',
    'api': 'mtop.taobao.idlemtopsearch.pc.search',
    'sessionOption': 'AutoLoginOnly',
    'spm_cnt': 'a21ybx.search.0.0',
    'spm_pre': 'a21ybx.search.searchInput.0',
}
token =cookies['_m_h5_tk'].split('_')[0]
print(token)
appKey = "34839810"
data_1 = f'{{"pageNumber":"{page}","keyword": "{keyword}","fromFilter":false,"rowsPerPage":30,"sortValue":"","sortField":"","customDistance":"","gps":"","propValueStr":{{}},"customGps":"","searchReqFromPage":"pcSearch","extraFilterValue":"{{}}","userPositionJson":"{{}}"}}'
 
i = ( token + "&" + time + "&" + appKey + "&" + data_1)
sign=md5(i.encode()).hexdigest()
params['sign']=sign
 
print(data,data_1)
 
response = requests.post(
    'https://h5api.m.goofish.com/h5/mtop.taobao.idlemtopsearch.pc.search/1.0/',
    params=params,
    cookies=cookies,
    headers=headers,
    data=data,
 
)
result=response.json()
print(result)
resultlist=result['data']['resultList']
 
for index in resultlist:
    try:
        name = index['data']['item']['main']['exContent']['userNickName']
    except:
        name = "未知"
    try:
        price = index['data']['item']['main']['exContent']['detailParams'][
            'soldPrice']
    except:
        price = "未知"
    shop_id = index['data']['item']['main']['exContent']['detailParams'][
        'itemId']
    shop_link = f'https://www.goofish.com/item?id=893424239322&categoryId={shop_id}'
 
    dit = {"用户名": name,
           "地区": index['data']['item']['main']['exContent']['area'],
           "售价": price,
           "标题": index['data']['item']['main']['exContent']['detailParams'][
               'title'],
           '详情页': shop_link}
 
    fieldnames = [
        "用户名",
        "地区",
        "售价",
        "标题",
        '详情页']
 
    # 打开文件并写入数据
    import csv
    import os
 
    # 定义字段名
    fieldnames = [
        "用户名",
        "地区",
        "售价",
        "标题",
        "详情页"
    ]
 
 
    # 检查文件是否存在（决定是否需要写入表头）
 
 
    file_name = f"{keyword}.csv"
    file_path = os_path / file_name
    file_exists = os.path.isfile(f'["{file_name}.csv"]')
 
    # 打开文件并写入数据
    with open(file_path , mode="a", newline="", encoding="utf-8") as file:
        csv_writer = csv.DictWriter(file, fieldnames=fieldnames)
 
        # 如果文件不存在或为空，则写入表头
        if not file_exists:
            csv_writer.writeheader()
 
        # 写入一行数据
        csv_writer.writerow(dit)
 
    print(dit)