使用fiddler抓包工具,分析斗鱼接口信息找到斗鱼接口url,进行接口分析,提取数据。由于斗鱼直播数据和整个页面页码都是根据开播来实时更新的。所以我们提取数据是要判断。拿到实时的页码。
import requests
import random
'''
url = https://www.douyu.com/gapi/rkc/directory/0_0/list
'''
def get_douyu_api(url):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
}
proxies_list = [
{
'http': 'http://218.95.37.252:3128',
'https': 'https://182.61.162.160:3128'
},
{
'http': 'http://163.125.19.53:8888',
'https': 'https://221.229.252.98:8080'
},
]
proxies = random.choice(proxies_list)
print(proxies)
response = requests.get(url, headers=headers,proxies=proxies).json()
# 一个接口里120条数据(1页)
for i in range(120):
try:
# 直播标题
title = response['data']['rl'][i]['rn']
# print(title)
except:
title = '无标题'
try:
# 直播类型
type1 = response['data']['rl'][i]['c2name']
# print(type1)
except:
type1 = '无类型'
try:
# 主播名
name = response['data']['rl'][i]['nn']
# print(name)
except:
name = '无用户'
try:
# 热度
hot = response['data']['rl'][i]['ol']
# print(hot)
except:
hot = '无热度'
info = f"直播类型:{type1},直播标题:{title},主播名:{name},热度:{hot}"
print(info)
with open('斗鱼.txt','a',encoding='utf-8')as fp:
fp.write(info+'\n')
# 总页数
pgcnt = response['data']['pgcnt']
return pgcnt
# print(pgcnt)
if __name__ == '__main__':
i = 1
while True:
url = f'https://www.douyu.com/gapi/rkc/directory/0_0/{i}'
pgcnt = get_douyu_api(url)
i += 1
if i > pgcnt:
break