码迷,mamicode.com
首页 > 编程语言 > 详细

python3爬虫-网易云排行榜,网易云歌手及作品

时间:2019-04-25 01:11:33      阅读:141      评论:0      收藏:0      [点我收藏+]

标签:box   raise   pattern   main   cep   pen   spider   test   dict   

import requests, re, json, os, time
from fake_useragent import UserAgent
from lxml import etree
from urllib import parse


class MyError(Exception):
    def __init__(self, status, msg):
        self.status = status
        self.msg = msg


class WyRinking():
    def __init__(self):
        ua = UserAgent()
        self.stratUrl = "https://music.163.com/discover/toplist"
        self.headers = {
            "User-Agent": ua.random
        }
        self.timeout = 10
        self.allow_redirects = False
        self.nameList = []
        self.urlList = []

    def __getRinkNameUrl(self, response):
        ‘‘‘获取所有排行榜名字,和url‘‘‘
        html_selector = self.__etreeSelector(response)
        self.nameList = html_selector.xpath(
            "//div[contains(@class,‘item‘) and contains(@class,‘f-cb‘)]/p[@class=‘name‘]/a/text()") or []
        self.urlList = html_selector.xpath(
            "//div[contains(@class,‘item‘) and contains(@class,‘f-cb‘)]/p[@class=‘name‘]/a/@href") or []

    def __getPageHtml(self, url):
        ‘‘‘请求页面‘‘‘
        try:
            response = requests.get(url, headers=self.headers, timeout=self.timeout,
                                    allow_redirects=self.allow_redirects)
            return response
        except requests.exceptions.Timeout as e:
            print("Timeout Error>>:", e)
            self.__getPageHtml(url=url)

    def __getRankHtml(self):
        ‘‘‘获取每个排行榜的html源码‘‘‘
        if not self.nameList and not self.urlList:
            raise MyError(10000, "{},{} 数据不能为空".format(self.nameList, self.urlList))
        if len(self.nameList) != len(self.urlList):
            raise MyError(10001, "nameList,urlList数据不能一一对应")
        for i in range(len(self.urlList)):
            url = parse.urljoin(self.stratUrl, url=self.urlList[i])
            response = self.__getPageHtml(url=url)
            response.customizeName = self.nameList[i]
            self.__getRankInfo(response)

    def __getRankInfo(self, response):
        ‘‘‘获取到网页中的json格式数据,写入到文件‘‘‘
        html_selector = self.__etreeSelector(response)

        test = html_selector.xpath("//*[@id=‘song-list-pre-data‘]/text()")[0] or ""
        updateTime = html_selector.xpath("//span[contains(@class,‘sep‘) and contains(@class,‘s-fc3‘)]/text()")[0]
        try:
            data = json.loads(test)
        except json.decoder.JSONDecodeError:
            data = json.loads(test + "}}])
        ‘‘‘
        if not len(songNmaeList) == len(songUrlList) == len(songIdList) == len(songIdList):
            raise MyError(10001, "songNmaeList,songUrlList,songIdList,songIdList数据不能一一对应")
        ‘‘‘
        fileName = response.customizeName + -- + updateTime + ".json"
        if not Rink_BASE_PATH:
            raise MyError(10005, "需要在全局中配置该参数Rink_BASE_PATH,用于文件存放地址")
        if not os.path.exists(Rink_BASE_PATH):
            os.makedirs(Rink_BASE_PATH)
        path = os.path.join(Rink_BASE_PATH, fileName)
        self.__writeToFile(path, data)

    def __writeToFile(self, path, data):
        print(正在写入文件{}.json.format(path))
        index = 1
        with open(path, "w", encoding="utf-8") as f:
            for data_dic in data:
                dic = {}
                dic["rankNum"] = index
                dic["songId"] = data_dic.get("id")
                dic["songName"] = data_dic.get("name")
                dic["artistsInfo"] = data_dic.get("artists")
                dic["commentThreadId"] = data_dic.get("commentThreadId")
                f.write(json.dumps(dic, ensure_ascii=False) + "\n")
                index += 1

    def __reSongId(self, songurl: str):
        ‘‘‘
        :param songurl:  /song?id=1336871144 格式类似于这样
        ‘‘‘
        pattern = r"id=(\d+)"
        try:
            id = re.findall(pattern, songurl)[0]
        except IndexError:
            raise MyError(10002, "歌曲id获取失败")
        return id

    def collectRanking(self):
        ‘‘‘获取网易云排行榜数据‘‘‘
        response = self.__getPageHtml(url=self.stratUrl)
        self.__getRinkNameUrl(response)
        self.__getRankHtml()

    def __etreeSelector(self, response):
        ‘‘‘将response对象转换为xml格式‘‘‘
        return etree.HTML(response.text)


class WySinger():
    __isFirstStatus = True  # 请求华语男歌手页面的时候,获取到A-Z对应的参数,这个只需要获取一次就足够

    def __init__(self):
        ua = UserAgent()
        self.stratUrl = "https://music.163.com/discover/artist"
        self.headers = {
            "User-Agent": ua.random
        }
        self.timeout = 10
        self.allow_redirects = False
        self.sCategoryNameList = []
        self.sCategoryIdList = []
        self.sCategoryUrlList = []
        self.initialIdList = []
        self.markList = []

    def __getPageHtml(self, url):
        ‘‘‘请求页面‘‘‘
        try:
            response = requests.get(url, headers=self.headers, timeout=self.timeout,
                                    allow_redirects=self.allow_redirects)
            return response
        except requests.exceptions.Timeout as e:
            print("Timeout Error>>:", e)
            self.__getPageHtml(url=url)

    def __getSingerCategory(self, response):
        htmlSelector = self.__etreeSelector(response)
        sCategoryNameList = htmlSelector.xpath(
            "//*[@id=‘singer-cat-nav‘]/div[@class=‘blk‘]//li/a[@class=‘cat-flag‘]/text()")
        sCategoryIdList = htmlSelector.xpath(
            "//*[@id=‘singer-cat-nav‘]/div[@class=‘blk‘]//li/a[@class=‘cat-flag‘]/@data-cat")
        sCategoryUrlList = htmlSelector.xpath(
            "//*[@id=‘singer-cat-nav‘]/div[@class=‘blk‘]//li/a[@class=‘cat-flag‘]/@href")
        if sCategoryUrlList and len(sCategoryNameList) == len(sCategoryIdList) == len(sCategoryUrlList):
            self.sCategoryNameList = sCategoryNameList or []
            self.sCategoryIdList = sCategoryIdList or []
            self.sCategoryUrlList = [parse.urljoin(self.stratUrl, url) for url in sCategoryUrlList or []]

    def __getSingerListPage(self):
        if not self.sCategoryNameList and not self.sCategoryUrlList:
            raise MyError(10000, "{},{} 数据不能为空".format(self.sCategoryNameList, self.sCategoryUrlList))
        if len(self.sCategoryNameList) != len(self.sCategoryUrlList):
            raise MyError(10001, "nameList,urlList数据不能一一对应")
        for sCategoryUrl in self.sCategoryUrlList:
            response = self.__getPageHtml(sCategoryUrl)
            if self.__isFirstStatus:
                self.__getInitialId(response)
                self.__isFirstStatus = False

            for inintalId in self.initialIdList:
                if inintalId == "-1":
                    # inintalId 为-1的时候代表热门,但是会和后面的歌手信息重复,所以做个判断
                    continue
                url = sCategoryUrl + "&initial=" + inintalId
                res = self.__getPageHtml(url)
                yield res

    def __getSingerIdUrl(self, response):
        htmlSelector = self.__etreeSelector(response)
        aSelector = htmlSelector.xpath(
            "//*[@id=‘m-artist-box‘]//a[@class=‘msk‘] | //*[@id=‘m-artist-box‘]/li[@class=‘sml‘]/a[1]")
        singerUrlList = [parse.urljoin(self.stratUrl, selector.xpath("@href")[0]) for selector in aSelector]
        singerNameList = [selector.xpath("@title")[0].replace("的音乐", "") for selector in aSelector]
        if singerUrlList and len(singerUrlList) == len(singerNameList):
            yield list(zip(singerUrlList, singerNameList))
        else:
            yield []

    def __getInitialId(self, response):
        ‘‘‘获取A-Z对应的initialId‘‘‘
        htmlSelector = self.__etreeSelector(response)
        urlList = htmlSelector.xpath("//*[@id=‘initial-selector‘]/li/a/@href")
        initialIdList = [self.__reInitialId(url) for url in urlList]
        markList = htmlSelector.xpath("//*[@id=‘initial-selector‘]/li/a/text()")

        if len(initialIdList) == len(markList):
            self.initialIdList = initialIdList
            self.markList = markList

    def __reInitialId(self, url):
        ‘‘‘
        url格式为:/discover/artist/cat?id=1001&initial=-1
        ‘‘‘
        pattern = r"initial=(.*)"
        initialId = re.findall(pattern, url, re.S)[0]
        return initialId

    def __getSingerDetails(self, response):
        htmlSelector = self.__etreeSelector(response)
        try:
            data_json = htmlSelector.xpath("//*[@id=‘song-list-pre-data‘]/text()")[0]
            data_list = json.loads(data_json, strict=False)
            singerDetails_json = htmlSelector.xpath("//script[@type=‘application/ld+json‘]/text()")[0]
            singerDetails_dict = json.loads(singerDetails_json, strict=False)
            singerDetails_content = singerDetails_dict.get("description")
            return data_list, singerDetails_content
        except Exception as e:
            # 有些音乐人是没有音乐作品的,所以通过索引取值([0])就会抛异常,我这里捕捉改异常,不进行处理就好
            print(e)
            return None, None

    def __writeToFile(self, datalist, singerDetails_content, singerName):
        if not os.path.exists(Singer_BASE_PATH):
            os.makedirs(Singer_BASE_PATH)
        path = os.path.join(Singer_BASE_PATH, singerName)
        print("正在写入{}".format(singerName))
        with open(path + ".txt", w, encoding="utf-8") as f:
            f.write("歌手简介:{}".format(singerDetails_content) + "\n")
            for data in datalist:
                f.write("-" * 50 + "\n")
                f.write("歌曲名:{}".format(data.get("name")) + "\n")
                f.write("歌曲ID:{}".format(data.get("privilege").get("id")) + "\n")
                f.write("歌曲专辑:{}".format(data.get("album").get("name")) + "\n")
                f.write("歌曲别号:{}".format("" if not data.get("alias") else data.get("alias")) + "\n")

    def __etreeSelector(self, response):
        ‘‘‘将response对象转换为xml格式‘‘‘
        return etree.HTML(response.text)

    def collectSinger(self):
        response = self.__getPageHtml(url=self.stratUrl)
        self.__getSingerCategory(response)
        resGenerator = self.__getSingerListPage()
        for res in resGenerator:
            time.sleep(1)
            a = self.__getSingerIdUrl(res)  # a是一个生成器,不知道取啥名,它__next__就是一个列表,这个列表就是当前页面所有歌手名和url的元组
            for i in a:  # i 就是 a__next__得来的列表
                for b in i:  # b 就是我们想要的结果  一个元组(歌手名,歌手详情页的url)
                    singerUrl = b[0]
                    singerName = b[1]
                    singerResponse = self.__getPageHtml(singerUrl)
                    datalist, singerDetails_content = self.__getSingerDetails(singerResponse)
                    if not datalist and not singerDetails_content:
                        continue
                    self.__writeToFile(datalist, singerDetails_content, singerName)


if __name__ == __main__:
    Rink_BASE_PATH = r"D:\spidersData\Rinking"
    Singer_BASE_PATH = r"D:\spidersData\SingerInfo"
    wangyiyun = WyRinking()
    wangyiyun.collectRanking()  # 获取网易云排行榜数据
    wangyiyun = WySinger()
    wangyiyun.collectSinger()  # 获取网易云所有歌手及作品

 

python3爬虫-网易云排行榜,网易云歌手及作品

标签:box   raise   pattern   main   cep   pen   spider   test   dict   

原文地址:https://www.cnblogs.com/zhuchunyu/p/10765932.html

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!