爬取douyin主页时第一页数据

import requests
import json
from urllib import parse
import re
# 抖音视频的URL : Request URL: 
url="https://www.iesdouyin.com/web/api/v2/aweme/post/?sec_uid=MS4wLjABAAAAPiYAuTiuaI39UV-QJtyFYdT74-Y0NdNOddeS3JUaeWg&count=21&max_cursor=0&_signature=xHcvZwAApmfZvSVp7lyHfMR3L3"

headers = {
    'User-Agent':"Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1"
}
#调用requests中的get获取抖音作者主页的网页链接
r = requests.get(url=url, headers=headers,stream=True)
#输出访问状态，如为<200>即为访问成功
print("初始访问状态:",r)
#使用json解析获取的网页内容
data_json = json.loads(r.text)
#使用json解析网页后，data_json的内容为dict格式，我们可以通过以下方式查看健名
#print(data_json)
path='/'
for i in range(len(data_json['aweme_list'])):
        #url_1为我们获取的视频链接
        url_1 = data_json['aweme_list'][i]['video']['play_addr_lowbr']['url_list'][0]
        #t为我们获取的视频标题
        t = data_json['aweme_list'][i]['desc']
        # requests发送浏览器发送get请求，得到数据
        r = requests.get(url=url_1, headers=headers,stream=True)
        print(r)    #输出r访问状态
        # 获取数据的二进制长度
        reponse_body_lenth = int(r.headers.get("Content-Length"))
        # 打印数据的长度
        print("视频的数据长度为:", reponse_body_lenth)
        #path_1为完整文件保存路径
        path_1 = path+t+'.mp4'
        #去除文件名中特殊字符否则报错
        rstr = r"[\/\\\:;\*#￥%$!@^……&()\?\"\<\>\|]"  # '/ \ : * ? " < > |'
        path_1 = re.sub(rstr, "", path_1)  # 替换为""
        # 保存抖音视频mp4格式，二进制读取

　　　　　　#去除文件名中特殊字符否则报错
　　　　　　#rstr = r"[\/\\\:;\*#￥%$!@^……&()\?\"\<\>\|\s] " # '/ \ : * ? " < > |'
　　　　　　#path_1 = re.sub(rstr, "", path_1) # 替换为""
　　　　　　# 保存抖音视频mp4格式，二进制读取
　　　　　　#path_1 =path_1.replace("/","").replace('\n#',' ').replace(' #',' ')
　　　　　　#with open(path_1, "wb") as xh:

        with open(path_1, "wb") as xh:
            # 先定义初始进度为0
            write_all = 0
            for chunk in r.iter_content(chunk_size=1000000):
                write_all += xh.write(chunk)
                # 打印下载进度
                print("下载进度：%02.6f%%" % (100 * write_all / reponse_body_lenth))

　　

使用中有报错，json解析错误：

json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
有可能是heder头传参数问题，包括格式与数据传输不足导致，这里添加了一个cookei就可以了

import requests
import json
from urllib import parse
import re
# 抖音视频的URL : Request URL:
#url="https://www.iesdouyin.com/web/api/v2/aweme/post/?sec_uid=MS4wLjABAAAAPiYAuTiuaI39UV-QJtyFYdT74-Y0NdNOddeS3JUaeWg&count=21&max_cursor=0&_signature=xHcvZwAApmfZvSVp7lyHfMR3L3"
url = "https://www.iesdouyin.com/web/api/v2/aweme/post/?reflow_source=reflow_page&sec_uid=MS4wLjABAAAA7gdVQLJr7WPYgx3YO90RZw9SU9DoJCgFVbvAwbd6kkQ&count=21&max_cursor=0&msToken=6u7tnUcZLCxkZ3I_bvz2Nm9EYGn6yTJq5f7YyvRVdFgCvoYt_6tvpDxBWiXczXekd_AYDc-xUFWffe1M7yUtIqRWgdkOlvXuRRT4KxFItTZS6Dr5u6Y8pyFI9sVujg==&X-Bogus=DFSzKwVOUKhANCFitc0FcF9WX7jS&_signature=_02B4Z6wo00001vG.7sAAAIDCcb0UgkgR9N7xr-pAANiFol76tIVSE6ObmhzdoBocqDTHelV68upzkUi6jjJr6FNy4kCFmZQ8Bxln96efDYyxEUR-oxiTX1Jnui7jAW3KWjMOFVJ7sszUVig69a";
headers = {
    'User-Agent':"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Mobile Safari/537.36",
    'cookie': "ttwid=1%7C8SJ6I0piwi6aLXcYCfO44e_ICVpTT7wImJ5bi31yH0w%7C1679115782%7C8138e7a0e3a9cc329791eaaa731418451697249b392e58a28cf987f27e4284e8; __ac_nonce=06417ab78003ab1d14e43; __ac_signature=_02B4Z6wo00f01TncvSwAAIDBud5HbZ28K5057LmAACpj8a; _tea_utm_cache_1243={%22utm_source%22:%22copy%22%2C%22utm_medium%22:%22android%22%2C%22utm_campaign%22:%22client_share%22}; s_v_web_id=verify_lfg3om5y_TIAGl8SV_p9PF_4kOf_9ThY_Pp4K2j7RHQo1; _tea_utm_cache_2018={%22utm_source%22:%22copy%22%2C%22utm_medium%22:%22android%22%2C%22utm_campaign%22:%22client_share%22}; msToken=6u7tnUcZLCxkZ3I_bvz2Nm9EYGn6yTJq5f7YyvRVdFgCvoYt_6tvpDxBWiXczXekd_AYDc-xUFWffe1M7yUtIqRWgdkOlvXuRRT4KxFItTZS6Dr5u6Y8pyFI9sVujg==; msToken=DQwwyXA5lreBS2fXFA-e8qh0B0oDVvZItWU2kl-qGbfa6a910HP1J_SuCTaH6alQPLRXtU-te0ZvCbCRgifaB5xZKP0W80VYgLew-UyrOzZZ_zDvnsVxt-Dri2NZNw==; ttcid=417a2e9adcf04735b4567e5d71b7d2a291; tt_scid=7YmVP3cRSd4tStECPikphUZGHF0bQ9TmfbfJJUBrILLhomHyOD3UXugYIFhia6pUdf37"
}
#调用requests中的get获取抖音作者主页的网页链接
r = requests.get(url=url, headers=headers,stream=True)
#输出访问状态，如为<200>即为访问成功
print("初始访问状态:",r)
#使用json解析获取的网页内容
data_json = json.loads(r.text)
#使用json解析网页后，data_json的内容为dict格式，我们可以通过以下方式查看健名
#print(data_json)
path='/'
for i in range(len(data_json['aweme_list'])):
        #url_1为我们获取的视频链接
        url_1 = data_json['aweme_list'][i]['video']['play_addr_lowbr']['url_list'][0]
        #t为我们获取的视频标题
        t = data_json['aweme_list'][i]['desc']
        # requests发送浏览器发送get请求，得到数据
        r = requests.get(url=url_1, headers=headers,stream=True)
        print(r)    #输出r访问状态
        # 获取数据的二进制长度
        reponse_body_lenth = int(r.headers.get("Content-Length"))
        # 打印数据的长度
        print("视频的数据长度为:", reponse_body_lenth)
        #path_1为完整文件保存路径
        path_1 = path+t+'.mp4'
        #去除文件名中特殊字符否则报错
        rstr = r"[\/\\\:;\*#￥%$!@^……&()\?\"\<\>\|]"  # '/ \ : * ? " < > |'
        path_1 = re.sub(rstr, "", path_1)  # 替换为""
        # 保存抖音视频mp4格式，二进制读取
        with open(path_1, "wb") as xh:
            # 先定义初始进度为0
            write_all = 0
            for chunk in r.iter_content(chunk_size=1000000):
                write_all += xh.write(chunk)
                # 打印下载进度
                print("下载进度：%02.6f%%" % (100 * write_all / reponse_body_lenth))