获得ValueError:未知的网址类型:' '

时间:2017-11-26 02:32:51

标签: python python-requests

我在下面的代码中迭代了一些曲目。然后对于每个曲目,我想使用musixmatch api根据艺术家姓名和曲目名称获取和打印曲目的歌词。

通过某些曲目迭代并打印歌词的代码:

for i, v in tracks.items():
    artist = tracks[i]['artist'].replace(" ", "+")
    title = tracks[i]['title'].replace(" ", "+")

    print(tracks)

    print(song_lyric(title, artist))

打印(曲目)以这种格式返回:

{12: {'trackID': 12, 'title': 'Achtung Baby', 'number': '1', 'artist': 'U2', 'album': 'Achtung Baby', 'albumID': 2, 'duration': '291'}

当代码退出时,会打印第一首曲目的歌词,但之后会出现错误:

Traceback (most recent call last):
  File "C:/Users/Ozzy/PycharmProjects/getData/getData.py", line 239, in <module>
    print(song_lyric(title, artist))
  File "C:/Users/Ozzy/PycharmProjects/getData/getData.py", line 72, in song_lyric
    lyrics_tracking(tracking_url)
  File "C:/Users/Ozzy/PycharmProjects/getData/getData.py", line 79, in lyrics_tracking
    request = urllib.request.Request(querystring)
  File "C:\Users\Ozzy\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 329, in __init__
    self.full_url = url
  File "C:\Users\Ozzy\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 355, in full_url
    self._parse()
  File "C:\Users\Ozzy\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 384, in _parse
    raise ValueError("unknown url type: %r" % self.full_url)
ValueError: unknown url type: ''

你知道为什么会出现这个错误吗?

从musixmatch获取歌词的方法是公开的:

def song_lyric(song_name, artist_name):
    while True:
        querystring = apiurl_musixmatch + "matcher.lyrics.get?q_track=" + urllib.parse.quote(
            song_name) + "&q_artist=" + urllib.parse.quote(
            artist_name) + "&apikey=" + apikey_musixmatch + "&format=json&f_has_lyrics=1"
        # matcher.lyrics.get?q_track=sexy%20and%20i%20know%20it&q_artist=lmfao
        request = urllib.request.Request(querystring)
        # request.add_header("Authorization", "Bearer " + client_access_token)
        request.add_header("User-Agent",
                           "curl/7.9.8 (i686-pc-linux-gnu) libcurl 7.9.8 (OpenSSL 0.9.6b) (ipv6 enabled)")  # Must include user agent of some sort, otherwise 403 returned
        while True:
            try:
                response = urllib.request.urlopen(request,
                                                  timeout=4)  # timeout set to 4 seconds; automatically retries if times out
                raw = response.read()
            except socket.timeout:
                print("Timeout raised and caught")
                continue
            break
        json_obj = json.loads(raw.decode('utf-8'))
        body = json_obj["message"]["body"]["lyrics"]["lyrics_body"]
        copyright = json_obj["message"]["body"]["lyrics"]["lyrics_copyright"]
        tracking_url = json_obj["message"]["body"]["lyrics"]["html_tracking_url"]
        #print(tracking_url)
        lyrics_tracking(tracking_url)
        return (body + "\n\n" + copyright)


def lyrics_tracking(tracking_url):
    while True:
        querystring = tracking_url
        request = urllib.request.Request(querystring)
        # request.add_header("Authorization", "Bearer " + client_access_token)
        request.add_header("User-Agent",
                           "curl/7.9.8 (i686-pc-linux-gnu) libcurl 7.9.8 (OpenSSL 0.9.6b) (ipv6 enabled)")  # Must include user agent of some sort, otherwise 403 returned
        try:
            response = urllib.request.urlopen(request,
                                              timeout=4)  # timeout set to 4 seconds; automatically retries if times out
            raw = response.read()
        except socket.timeout:
            print("Timeout raised and caught")
            continue
        break
        print(raw)

重现错误的完整工作示例:

import requests
import json
import urllib.request, urllib.error, urllib.parse
import socket

apikey_musixmatch = '0b4a363bbd71974c2634837d5b5d1d9a' #generated for the example
apiurl_musixmatch = 'http://api.musixmatch.com/ws/1.1/'

api_key = "b088cbedecd40b35dd89e90f55227ac2" #generated for the example
def song_lyric(song_name, artist_name):
    while True:
        querystring = apiurl_musixmatch + "matcher.lyrics.get?q_track=" + urllib.parse.quote(
            song_name) + "&q_artist=" + urllib.parse.quote(
            artist_name) + "&apikey=" + apikey_musixmatch + "&format=json&f_has_lyrics=1"
        # matcher.lyrics.get?q_track=sexy%20and%20i%20know%20it&q_artist=lmfao
        request = urllib.request.Request(querystring)
        # request.add_header("Authorization", "Bearer " + client_access_token)
        request.add_header("User-Agent",
                           "curl/7.9.8 (i686-pc-linux-gnu) libcurl 7.9.8 (OpenSSL 0.9.6b) (ipv6 enabled)")  # Must include user agent of some sort, otherwise 403 returned
        while True:
            try:
                response = urllib.request.urlopen(request,
                                                  timeout=4)  # timeout set to 4 seconds; automatically retries if times out
                raw = response.read()
            except socket.timeout:
                print("Timeout raised and caught")
                continue
            break
        json_obj = json.loads(raw.decode('utf-8'))
        body = json_obj["message"]["body"]["lyrics"]["lyrics_body"]
        copyright = json_obj["message"]["body"]["lyrics"]["lyrics_copyright"]
        tracking_url = json_obj["message"]["body"]["lyrics"]["html_tracking_url"]
        print("Tracking_url====================" +tracking_url + "==================================")
        lyrics_tracking(tracking_url)
        return (body + "\n\n" + copyright)


def lyrics_tracking(tracking_url):
    while True:
        querystring = tracking_url
        request = urllib.request.Request(querystring)
        # request.add_header("Authorization", "Bearer " + client_access_token)
        request.add_header("User-Agent",
                           "curl/7.9.8 (i686-pc-linux-gnu) libcurl 7.9.8 (OpenSSL 0.9.6b) (ipv6 enabled)")  # Must include user agent of some sort, otherwise 403 returned
        try:
            response = urllib.request.urlopen(request,
                                              timeout=4)  # timeout set to 4 seconds; automatically retries if times out
            raw = response.read()
        except socket.timeout:
            print("Timeout raised and caught")
            continue
        break
        print(raw)

ID = 0

#get top artists from country
artists = {}
for i in range(2, 3):
    artists_response = requests.get(
        'http://ws.audioscrobbler.com/2.0/?method=geo.gettopartists&country=spain&format=json&page=' + str(i) + '&api_key=' + api_key)
    artists_data = artists_response.json()
    for artist in artists_data["topartists"]["artist"]:


        name = artist["name"]
        url = artist["url"]
        if ID > 1: continue
        artists[ID] = {}
        artists[ID]['ID'] = ID
        artists[ID]['name'] = name
        ID += 1

    for i, v in artists.items():
        chosen = artists[i]['name'].replace(" ", "+")
        artist_response = requests.get(
            'http://ws.audioscrobbler.com/2.0/?method=artist.getinfo&format=json&artist=' + chosen + '&api_key=' + api_key)
        artist_data = artist_response.json()


# get top albums of the artists
albums = {}
for i, v in artists.items():
    chosen = artists[i]['name'].replace(" ", "+")
    topalbums_response = requests.get(
        'http://ws.audioscrobbler.com/2.0/?method=artist.gettopalbums&format=json&artist=' + chosen + '&api_key=' + api_key + '&limit=5')
    albums_data = topalbums_response.json()

    for album in albums_data['topalbums']['album']:
        name = album["name"]
        url = album["url"]

        albums[ID] = {}
        albums[ID]['ID'] = ID
        albums[ID]['artist'] = artists[i]['name']
        albums[ID]['artistID'] = artists[i]['ID']
        albums[ID]['name'] = name

        ID += 1

# Get tracks of the album

tracks = {}
for i, v in albums.items():
    artist = albums[i]['artist'].replace(" ", "+")
    name = albums[i]['name'].replace(" ", "+")
    album_response_data = requests.get(
        'http://ws.audioscrobbler.com/2.0/?method=album.getinfo&format=json&api_key=' + api_key + '&artist=' + artist + '&album=' + name)
    album_response = album_response_data.json()



    for album in album_response['album']['tracks']['track']:
        title = album['name']
        tracks[ID] = {}
        tracks[ID]['trackID'] = ID
        tracks[ID]['title'] = title
        tracks[ID]['artist'] = albums[i]['artist']
        tracks[ID]['album'] = albums[i]['name']
        tracks[ID]['albumID'] = albums[i]['ID']

        ID += 1

for i, v in tracks.items():
    artist = tracks[i]['artist'].replace(" ", "+")
    title = tracks[i]['title'].replace(" ", "+")

    # print the lyric of each track
    print(song_lyric(title, artist))

1 个答案:

答案 0 :(得分:2)

似乎网址不正确。它发生在这里: tracking_url = json_obj["message"]["body"]["lyrics"]["html_tracking_url"] 如果您能够在本地运行该API并查看返回到tracking_url的内容,则可以找出它仍然存在的问题。

更新

我重现了它,因此urllib.request无法处理空字符串网址:"",这就是为什么你需要检查tracking_url != ""是否只有非空字符串或者你是需要请求这首歌。