[爬虫][5月8日代码更新]虎X直播{一起看}板块的超清直播源

本文来源吾爱破解论坛

本帖最后由 wushaominkk 于 2019-6-6 21:17 编辑



【请勿用于商业用途】
虎牙直播源m3u8

新手可以学习一下


一开始用的直接通过网页获取房间id
找不到翻页的, 然后换了思路,从接口
上获取直播间的id
这个代码可以爬其他板块的,其他板块的时候,
可能会遇到报错,稍微改一下就行了


导出txt文档,代码已补充


[Python] 纯文本查看 复制代码

import requests
import re
import json
from lxml import etree


class Huya_live:
 
    def __init__(self):
        # self.list_url = []
        self.id = []
        self.headers = {
                "user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36",
            }
 
    def get_m3u8(self):
        for id in self.id:
            url = "https://www.huya.com/" + id
            response = requests.get(url, headers=self.headers)
            html = response.text
            # title = re.findall("<title>.*|\r\n</title>", html)[0]
            html_etree = etree.HTML(html)
            title = html_etree.xpath('//h1[@id="J_roomTitle"]/text()')[0]
            title = re.sub("<title>|</title>|\r|\n", "", title)
            regex = re.compile(r"{.*}")#匹配{}格式的内容
            strs = re.findall(regex, html)
            if id == "523923" or id == "627859" or id == "880219" or id == "11602041" or id == "11352941" or id == "11352969" or id == "880203" or id == "11342439" or id == "17089810":
                    str = strs[1].replace("(|)", "")[:-1]
            else:
                str = strs[2].replace("(|)", "")[:-1]
            str = json.loads(str)
            try:
                streamName = "/" + str['data'][0]['gameStreamInfoList'][1]['sStreamName']
                m3u8 = str['data'][0]['gameStreamInfoList'][1]['sHlsUrl']
                # flv = str['data'][0]['gameStreamInfoList'][1]['sFlvUrl']
                print(title, "\t\t\t\t", m3u8+streamName + ".m3u8")
            except:
                print(url, "获取失败")
                continue
            self.put_write( m3u8 + streamName + ".m3u8", title)
 
    # def get_hrefs(self):
    #     base_url = "https://www.huya.com/g/seeTogether"
    #     response = requests.get(base_url, headers=self.headers).text
    #     html = etree.HTML(response)
    #     hrefs = html.xpath('//li[@class="game-live-item"]/a/@href')
    #     for href in hrefs[::2]:
    #         self.list_url.append(href)
 
    def get_romId(self):
 
        for i in range(1, 5):
            yiqikan_Api = "https://www.huya.com/cache.php?m=LiveList&do=getLiveListByPage&gameId=2135&tagAll=0&page=%d" % i
            # xingshow_api = "https://www.huya.com/cache.php?m=LiveList&do=getLiveListByPage&gameId=1663&tagAll=0&page=%d" % i
            response = requests.get(yiqikan_Api, headers=self.headers).text
            html = json.loads(response)
            ids = html['data']['datas']
            for id in ids:
                self.id.append(id['profileRoom'])

    def put_write(self, m3u8, title):
        str = title + "***"*20 + m3u8 + "\n"
        with open("./虎牙直播源.txt", 'a+') as f:
            f.write(str)
            
if __name__ == '__main__':
    huya = Huya_live()
    # huya.get_hrefs()
    huya.get_romId()
    huya.get_m3u8()

import re
import requests
import json
from lxml import etree


class Huya_live:

    def __init__(self):
        # self.list_url = []
        self.id = []
        self.headers = {
            "user-agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36",
        }

    def get_m3u8(self):
        for id in self.id:
            url = "https://www.huya.com/" + id
            response = requests.get(url, headers=self.headers)
            html = response.text
            # title = re.findall("<title>.*|\r\n</title>", html)[0]
            html_etree = etree.HTML(html)
            title = html_etree.xpath('//h1[@id="J_roomTitle"]/text()')[0]
            title = re.sub("<title>|</title>|\r|\n", "", title)
            regex = re.compile(r"{\"status\"(.*)};")  # 匹配{}格式的内容
            strs = re.findall(regex, html)

            try:
                a = list(list(strs)[0])
                a[4] = "{"
                str = "".join(a[4:])
                str = json.loads(str)
                streamName = "/" + str['data'][0]['gameStreamInfoList'][1]['sStreamName']
                m3u8 = str['data'][0]['gameStreamInfoList'][1]['sHlsUrl']
                # flv = str['data'][0]['gameStreamInfoList'][1]['sFlvUrl']
                print(title, "\t\t\t\t", m3u8 + streamName + ".m3u8")
            except:
                print(url, "直播间没有人直播噢, 不信你去看看 网址为%s" % url)
                continue
            self.put_write(m3u8 + streamName + ".m3u8", title)

    def get_romId(self):

        for i in range(1, 5):
            yiqikan_Api = "https://www.huya.com/cache.php?m=LiveList&do=getLiveListByPage&gameId=2135&tagAll=0&page=%d" % i
            # xingshow_api = "https://www.huya.com/cache.php?m=LiveList&do=getLiveListByPage&gameId=1663&tagAll=0&page=%d" % i
            response = requests.get(yiqikan_Api, headers=self.headers).text
            html = json.loads(response)
            ids = html['data']['datas']
            for id in ids:
                self.id.append(id['profileRoom'])

    def put_write(self, m3u8, title):
        str = title + "***" * 20 + m3u8 + "\n"
        with open("./虎牙直播源.txt", 'a+') as f:
            f.write(str)


if __name__ == '__main__':
    
    huya = Huya_live()
    huya.get_romId()
    huya.get_m3u8()