最近工作之余会听听评书,但主流门户收费加广告着实让人烦躁。作为IT人,怎能如此顺应别人家的产品规则。
下面以 python + taro 为例,写一个爬虫 + 小程序的播放应用:
最终实现的效果如下:
1132488286.jpg
原本听的喜马拉雅,但是资源有限。找到了个简陋的听书站点,资源是有了,但是广告一堆、交互生硬,谈不上用户体验了。
所以,爬它
爬虫
脚本不多,大概说下步骤:
获取全本的播放页面链接
循环页面链接获取每回的实际播放链接
重新组织数据结构打印输出
最终要的就是打印的 这个数据
完整脚本如下:
# -*-coding:utf-8-*-
import requests
from bs4 import BeautifulSoup
session = requests.session()
headers = {
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:58.0) Gecko/20100101 Firefox/58.0',
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'accept-language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
'accept-encoding': 'gzip, deflate, br',
}
def getHrefs(url):
r = session.get(url,headers=headers, verify=False)
r.encoding = 'GBK'
soup = BeautifulSoup(r.text, 'lxml')
rich_media_content = soup.find_all('div', class_='player')
playDatas = []
for item in rich_media_content:
playData = item.find("a").attrs['href']
playData = playData.replace('//','http://')
playData = playData.replace('play','playdata')
playDatas.append({
'playData': playData,
'title': item.find("a").text
})
return playDatas
def getPlayUrls(bookTitle, playDatas):
if len(playDatas) == 0:
return
playUrls = []
for index, item in enumerate(playDatas):
r = session.post(item['playData'], headers=headers, verify=False)
resp = r.json()
playUrls.append({
'playUrl': resp['urlpath'].replace('flv','mp3'),
'title': '{bookTitle}-{title}'.format(bookTitle=bookTitle, title=item['title']),
'id': index,
'played': 0,
})
return playUrls
if __name__ == "__main__":
bookTitle = 'xxxx第六部'
playDatas = getHrefs('http://xxxx.xxxx.xxx/xxxxx/')
playUrls = getPlayUrls(bookTitle, playDatas)
print(playUrls)
小程序
既然是给自己用的,就没必要搞的太复杂了。直接把爬到的数据放应用本地吧,加上一个播放列表,一个播放详情页面即可。
我本身用react较顺手,选择了Taro框架写小程序,顺便用了下Taro-UI组件库。
列表页面
...
componentDidShow () {
const songId = Taro.getStorageSync('songId')
const songList = Taro.getStorageSync('songList')
if (songList) {
this.setState({listData: songList})
}else {
Taro.setStorageSync('songList', this.state.listData)
}
if (songId) {
this.setState({ songId })
}
}
...
{listData && listData.map((item,index) => (
title={item.title}
arrow='right'
extraText={this.getExtraText(songId,item)}
onClick={()=>this.handleClick(index)}
/>
))}
详情页面
详情页面主要做的是:获取从列表来的ID,播放这个回目,播放控制,自动下一首,记录当前播放的回目及时间。
核心代码如下
...
startPlay = (itemIndex) => {
const songId = Taro.getStorageSync('songId')
let playTime = 0
if (songId && songId.toString() === itemIndex.toString()) {
playTime = Taro.getStorageSync('playTime')
}
const {listData} = this.state;
const musicInfo = {
name: listData[itemIndex].title,
playUrl: listData[itemIndex].playUrl,
itemIndex: parseInt(itemIndex),
playTime: playTime
}
this.setState({
musicInfo,
}, () => {
Taro.setNavigationBarTitle({title: listData[itemIndex].title})
this.autoPlay(musicInfo)
})
}
...
autoPlay = (musicInfo) => {
const bgMusic = Taro.getBackgroundAudioManager();
this.setState({
myAudio: bgMusic
},() => {
const songList = Taro.getStorageSync('songList')
songList[musicInfo.itemIndex].played = 1;
Taro.setStorageSync('songList', songList)
})
Taro.setStorageSync('songId', musicInfo.itemIndex)
bgMusic.src = musicInfo.playUrl
bgMusic.title = musicInfo.name
if (musicInfo.playTime > 0) {
bgMusic.startTime = musicInfo.playTime
}else {
bgMusic.startTime = 0
}
bgMusic.onTimeUpdate(() => {
this.setState({
timeLenght: bgMusic.duration,
playTime: bgMusic.currentTime
}, () => {
Taro.setStorageSync('playTime', bgMusic.currentTime)
})
})
bgMusic.onEnded(() => {
this.next();
})
bgMusic.onError(() => {
Taro.atMessage({
'message': '播放错误,自动播放下一首',
'type': 'error',
'duration': 1500
})
setTimeout(() => {
this.next();
}, 2000)
})
}
ok, 打开微信开发者工具,加载打包文件,扫个体验码,自嗨去吧~~