我正在编写一个脚本来抓取一个网站并下载当前的mp3文件，它使用BeautifulSoup和Python 3.6.3将所有链接抓取到各个艺术家页面中，但是一些抓取的网址包含的内容超过了一个＆＃34;。＆＃34;在它和我开火时
request.get(url, header=<random header using fake_useragent>)
它不会下载该文件，我该如何更正？
例如：
URL > abc.com/mp3/artist/songs/song.com.mp3 (not downloading)
URL > abc.com/mp3/artist/songs/song.mp3 (downloading)
代码：
def download_mp3(url_list_file, download_dir):
with open(url_list_file, 'r', encoding='utf-8') as urls:
for url in urls:
ua = fake_useragent.UserAgent(verify_ssl=False)
#header = {'User-Agent': str(ua.chrome.random)}
artist_dir = url.split('/')[4]
song_name = url.split('/')[6].replace('\n', '')
#corrected_url = ('path:url')
#print(corrected_url)
download_to = os.path.join(download_dir, artist_dir, song_name)
save_path = os.path.join(download_dir, artist_dir)
#print(download_to)
#print(save_path)
print(url)
if(os.path.isdir(save_path) == True):
#print ('True')
header = {'User-Agent': str(ua.random)}
lower_download_to = str.lower(song_name)
#To get correct file name
mp3_file_name = os.path.join(download_dir, artist_dir, lower_download_to.replace("www.", "").replace("[", "").replace("]", ""))
mp3_file = open(mp3_file_name, "wb")
temp_file = requests.get(url, headers=header)
mp3_file.write(temp_file.content)
time.sleep(random.randint(5,10))
else:
#print('False')
#To create Artist folder names
os.mkdir(save_path)
header = {'User-Agent': str(ua.random)}
lower_download_to = str.lower(download_to)
#To get correct file name
mp3_file_name = os.path.join(download_dir, artist_dir, lower_download_to.replace("www.", "").replace("[", "").replace("]", ""))
mp3_file = open(mp3_file_name, "wb")
temp_file = requests.get(url, headers=header)
mp3_file.write(temp_file.content)
time.sleep(random.randint(5,10))
urls.closed
答案 0 :(得分：0)
纠正了它 取代所有＆＃34;。＆＃34;在URL中除了最后一个＆＃34; .mp3＆＃34;使用百分比编码
string.replace（＆＃39;。＆＃39;，＆＃34;％2E＆＃34;，（string.count（＆＃39;。＆＃39;） - 1））< /强>