20240328爬虫代码记录

def get_com(request):
    print(requests)
    data = request.POST
    body_list = data['body_list'].split(',')
    Cookie = "SESSION=ZThmN2JiZjAtZjYyZC00NmY5LWI2ZWItMjM0ZmE5NjgwYjgz"
    # 定义请求头
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36",
        "Cookie": Cookie,
        "Referer": "http://eip.gmcc.net/poa/portalwork/workbench.do",
        "Host": "eip.gmcc.net",
        "Origin": "http://eip.gmcc.net",
        "Content-Type": "application/json;",

    }
    params = {
        "body": "kCudJ+vuZFWlavjw63JiCEHn00Aqgx12A8chqCL5wsw3sIvEwL6AV/u5tcsnutMKC7nLbBlgKbcDgzRdrYFhaf+0cApuGTSBUdJxyFocAvoGh9dUK6Zu+kX7nj7/UihJlyWuAKZY4smMwd7na5Ybfg==",

    }
    checkphone_url = "http://eip.gmcc.net/poa/addressBook/queryUsersPageList.do"

    df = pd.DataFrame()
    row_index = 0
    page_index = 0
    for body in body_list:
        print(page_index)
        page_index+=1
        params['body'] = body
        response = requests.post(checkphone_url, headers=headers, params=params)
        r_data = response.json()
        data_list = r_data['resultData']['list']
        for row in data_list:
            df.loc[row_index, 'fullName'] = row['fullName']
            df.loc[row_index, 'employee'] = row['employee']
            df.loc[row_index, 'company'] = row['company']
            df.loc[row_index, 'branch'] = row['branch']
            df.loc[row_index, 'department'] = row['department']
            df.loc[row_index, 'userGrade'] = row['userGrade']
            df.loc[row_index, 'title'] = row['title']
            df.loc[row_index, 'telePhone'] = row['telePhone']
            df.loc[row_index, 'email'] = row['email']
            row_index += 1

    df.to_excel("通讯录.xlsx")
    return JsonResponse({"res": "成功"})