def save_music(self, album_id):
params = {'id': album_id}
# 获取专辑对应的页面
r = requests.get('http://music.163.com/album',
headers=self.headers,
params=params)
# 网页解析
soup = BeautifulSoup(r.content.decode(), 'html.parser')
body = soup.body
album_name = body.find('div', attrs={'class': 'tit'}).find('h2').text
musics = body.find('ul', attrs={
'class': 'f-hide'
}).find_all('li') # 获取专辑的所有音乐
music_list = []
for music in musics:
music = music.find('a')
music_id = music['href'].replace('/song?id=', '')
music_name = music.getText()
music_list.append(music_name)
print("专辑id：%s, 专辑名：%s" % (album_id, album_name))
print(music_list)
for music in musics:
music = music.find('a')
music_id = music['href'].replace('/song?id=', '')
music_name = music.getText()
sql.insert_music(music_id, music_name, album_id, album_name)
def save_music(self, album_id):
# 获取歌手数据
try:
item = sql.get_artist(album_id)
except Exception as e:
# 打印错误日志
print(e)
params = {'id': album_id}
# 获取专辑对应的页面
r = requests.get('http://music.163.com/album',
headers=self.headers,
params=params)
# 网页解析
soup = BeautifulSoup(r.content.decode(), 'html.parser')
body = soup.body
musics = body.find('ul', attrs={
'class': 'f-hide'
}).find_all('li') # 获取专辑的所有音乐
for music in musics:
music = music.find('a')
music_id = music['href'].replace('/song?id=', '')
music_name = music.getText()
sql.insert_music(music_id, music_name, album_id, item[0], item[1])
def save_comments(musics, flag, connection0):
for i in musics:
try:
comments = my_music.save_content(i["music_id"],flag)
# comments = my_music.save_content()
# print(comments)
if comments["total"] > 0 :
hotList = []
for j in comments['hotComments']:
hotList.append(j["content"])
sql.insert_music(i["music_id"], comments['total'], ':'.join(hotList), connection0)
except Exception as e:
# 打印错误日志
print("error:"+str(i) + ': ' + str(e))
# print(str(e))
time.sleep(5)
def save_music(self,album_id):
params = {'id': album_id}
r = requests.get('http://music.163.com/album', headers=self.headers, params=params)
r.encoding = 'utf-8'
# self.writeFile(r"./music.txt", r.content)
# print(r.text[200:30000])
soup = BeautifulSoup(r.content, 'html.parser')
body = soup.body
all_music = body.find('ul', attrs={'class': 'f-hide'}).find_all('a')
# i["href"] = '/album?id=none'
for i in all_music:
music_id = i["href"].replace('/song?id=', '').strip()
music_name = i.string
# name = i.string
print(music_id,album_id,music_name)
sql.insert_music(music_name,album_id,music_id)
def save_music(self, artist_id):
params = {'id': artist_id}
# 获取专辑对应的页面
r = requests.get('http://music.163.com/artist',
headers=self.headers,
params=params)
# 网页解析
soup = BeautifulSoup(r.content.decode('utf-8'), 'html.parser')
body = soup.body
musics = body.find('ul', attrs={
'class': 'f-hide'
}).find_all('li') # 获取专辑的所有音乐
artist_name = body.find('h2', attrs={'id': 'artist-name'}).getText()
for music in musics:
music = music.find('a')
music_id = music['href'].replace('/song?id=', '')
music_name = music.getText()
sql.insert_music(music_id, music_name, artist_name)
def save_music(self, album_id):
params = {'id': album_id}
# 获取专辑对应的页面
# 这里做一个cookie切换
num = random.randint(0, 2)
if num == 0:
r = requests.get('http://music.163.com/album', headers=self.headers_one, params=params)
elif num == 1:
r = requests.get('http://music.163.com/album', headers=self.headers_two, params=params)
else:
r = requests.get('http://music.163.com/album', headers=self.headers_there, params=params)
# 网页解析
soup = BeautifulSoup(r.content.decode(), 'html.parser')
body = soup.body
# 取到ul class 然后再找li
musics = body.find('ul', attrs={'class': 'f-hide'}).find_all('li') # 获取专辑的所有音乐
for music in musics:
music = music.find('a')
music_id = music['href'].replace('/song?id=', '')
music_name = music.getText()
print(num)
print(music_name)
sql.insert_music(music_id, music_name, album_id)
def save_music(self, album_id):
params = {'id': album_id}
# 获取专辑对应的页面
r = requests.get('http://music.163.com/album',
headers=self.headers,
params=params,
proxies=proxies)
# 网页解析
soup = BeautifulSoup(r.content.decode(), 'html.parser')
body = soup.body
if body is not None:
musics = body.find('ul', attrs={
'class': 'f-hide'
}).find_all('li') # 获取专辑的所有音乐
for music in musics:
music = music.find('a')
music_id = music['href'].replace('/song?id=', '')
music_name = music.getText()
print(music_id, music_name, album_id)
sql.insert_music(music_id, music_name, album_id)
else:
print("Album {}'s music list's body is empty...".format(album_id))