import requests
import json
class Spider:
def __init__(self):
# 在这里不指定具体抓取哪一页,page=???,指定具体页数在后面
self.url = 'https://www.huya.com/cache.php?m=LiveList&do=getLiveListByPage&tagAll=0&page={}'
def parse(self, url):
response = requests.get(url)
response.encoding = 'utf-8'
assert response.status_code == 200 # 断言一下状态码是200
json_dict = json.loads(response.text) # 把响应的json数据转换成python的字典
infos = json_dict['data']['datas'] # 每一页的直播间数据全在这里面,一共120个
for info in infos:
item = {}
item['标题'] = info['introduction']
item['类型'] = info['gameFullName']
item['主播'] = info['nick']
item['网址'] = 'https://www.huya.com/' + info['profileRoom']
item['人气'] = info['totalCount']
print(item)
f.write(json.dumps(item, ensure_ascii=False)) # 为了防止乱码
f.write('\n')
f.write('\n')
if __name__ == '__main__':
spider = Spider()
with open('./huay.txt', 'a', encoding='utf-8') as f: # 将保存到本地的huya.txt文件中
for i in range(1, 11): # 在这里我只构造了1-10页的数据
spider.parse(spider.url.format(i))
获取虎牙直播所有地址代码,大神如何转换成php代码,浏览器输入http://域名/huya.php 直接获取全部一起看直播地址
发帖注意事项
请勿胡乱发帖:https://www.right.com.cn/forum/thread-8307840-1-1.html
账户手机验证:https://www.right.com.cn/forum/home.php?mod=spacecp&ac=plugin&id=jzsjiale_sms:home
|