def ana_song(weblink): # return song dictionary
ml = mylogger(logfile, get_funcname())
songmid = weblink.split('/')[-1]
songmid = songmid.split('.')[0]
ml.debug(songmid)
html = op_simple(weblink)[0]
bsObj = BeautifulSoup(html, "html.parser")
artist_name = bsObj.find('div', {'class': 'data__singer'})
artist_name = artist_name.attrs['title']
ml.debug(artist_name)
song_name = bsObj.find('h1', {'class': 'data__name_txt'})
song_name = modstr(song_name.text.strip())
ml.debug(song_name)
cover = bsObj.find('img', {'class': 'data__photo'})
cover = 'http:' + cover.attrs['src']
ml.debug('Cover link: ' + cover)
sDict = {
'artist': artist_name,
'song_name': song_name,
'songmid': songmid,
'cover': cover
}
ml.debug(sDict)
return sDict
def get_loc_one(song_id):
l = mylogger(logfile,get_funcname())
url = f'http://www.xiami.com/widget/xml-single/sid/{song_id}'
page = op_simple(url)
l.debug(page[1])
bsObj = BeautifulSoup(page[0],"html.parser") #;print(bsObj)
location = bsObj.find("location")
location = str(location)[19:-14]
if location == '':
l.debug('Track not published')
SongDic = {}
else:
l.debug('Raw Location: '+location)
location = decry(location)
song = bsObj.find("song_name")
song = modstr(str(song)[20:-15])
singer = bsObj.find("artist_name")
singer = modstr(str(singer)[22:-17])
album = bsObj.find("album_name")
album = modstr(str(album)[21:-16])
cover = bsObj.find('album_cover')
cover = 'http:'+str(cover)[22:-17]
SongDic = {'location':location,'song':song,'cover':cover,\
'artist':singer,'singer':singer,'album':album}
l.debug(SongDic)
return SongDic
def get_songlocation(songid):
'''Get undecryted location from xml'''
url = f'https://emumo.xiami.com/widget/xml-single/sid/{songid}'
html = op_simple(url, headers)[0]
bsObj = BeautifulSoup(html, "html.parser")
location = bsObj.find('location').text
return location
def ana_song(weblink):
ml = mylogger(logfile, get_funcname())
html = op_simple(weblink, header)[0]
# html = op_requests(url,verify=False).content
bsObj = BeautifulSoup(html, "html.parser")
# ml.debug(bsObj)
# title = bsObj.find('title')
# print(title)
song_name = bsObj.find('em', {'class': 'f-ff2'})
songname = modstr(song_name.text.strip())
ml.info(songname)
aa = bsObj.findAll('p', {'class': 'des s-fc4'})
artistname = modstr(aa[0].span.a.text)
albumname = modstr(aa[1].a.text)
ml.info(artistname)
ml.info(albumname)
cover = bsObj.find('div', {'class': 'u-cover u-cover-6 f-fl'})
cover = cover.img.attrs['href']
ml.info(cover)
songmid = weblink.split('=')[-1]
sDict = {
'artist': artistname,
'song_name': songname,
'songmid': songmid,
'cover': cover
}
ml.debug(sDict)
return sDict
def ana_mono(page):
ml = mylogger(logfile,get_funcname())
html = op_simple(page,ran_header())[0]
bsObj = BeautifulSoup(html,"html.parser") #;print(bsObj)
author = bsObj.find('span',{'class':'title'}).text.strip()
title = bsObj.find('h1',{'class':'title'}).text.strip()
p = {'author':author,'title':title}
ml.debug(p)
return p
def ana_dy(page):
'''Analyze Douyin web'''
ml = mylogger(logfile,get_funcname())
html = op_simple(page,ran_header())[0]
bsObj = BeautifulSoup(html,"html.parser") #;print(bsObj)
author = bsObj.find('p',{'class':'name nowrap'}).text.strip()
title = bsObj.find('h1',{'class':'desc'}).text.strip()
p = {'author':author,'title':title}
ml.info(p)
return p
def ana_mono(page):
'''Analyze Mono web'''
ml = mylogger(logfile,get_funcname())
html = op_simple(page,ran_header())[0]
bsObj = BeautifulSoup(html,"html.parser") #;print(bsObj)
author = bsObj.find('span',{'class':'title'}).text.strip()
title = bsObj.find('h1',{'class':'title'}).text.strip()
p = {'author':author,'title':title}
ml.debug(p)
return p
def ana_album(weblink):
ml = mylogger(logfile, get_funcname())
html = op_simple(weblink, header=ran_header(ref=ref))[0]
bsObj = BeautifulSoup(html, "html.parser") #;print(bsObj)
album_name = bsObj.find('h1', {'class': 'data__name_txt'})
album_name = modstr(album_name.text)
ml.debug(album_name)
artist_name = bsObj.find('a', {'class': 'js_singer data__singer_txt'})
artist_name = modstr(artist_name.text)
ml.debug(artist_name)
year = bsObj.find(text=re.compile('^发行时间'))[5:9]
ml.debug(year)
cover = bsObj.find('img', {'id': 'albumImg'})
cover = 'http:' + cover.attrs['src']
ml.debug('Cover link: ' + cover)
fullname = artist_name + ' - ' + year + ' - ' + album_name
aDict = {
'album': album_name,
'artist': artist_name,
'year': year,
'cover': cover,
'fullname': fullname
}
song = bsObj.findAll('div', {'class': 'songlist__number'})
n = 0
songtmp = [] # name duplicate check
for i in song:
n += 1
tracknumber = i.text
ml.debug('Find track ' + str(tracknumber))
tmp = i.next_sibling.next_sibling
si = tmp.find('span', {'class': 'songlist__songname_txt'}).a
songmid = si.attrs['href'].split('/')[-1][:-5]
songname = si.text
if songname in songtmp:
songname = songname + '_' + tracknumber
songtmp.append(songname)
ml.debug(songname)
singers = tmp.parent.findAll('a', {'class': "singer_name"})
if len(singers) > 1:
s = list(map(lambda x: x.text, singers))
singer = ','.join(s)
else:
singer = singers[0].text
ml.debug(singer)
si = [songmid, songname, singer]
aDict[int(tracknumber)] = si
aDict['TrackNum'] = n
# ml.info(aDict)
return aDict # Album dictionary
def ana_wx(page):
ml = mylogger(logfile,get_funcname())
html = op_simple(page,ran_header())[0]
# print(html)
bsObj = BeautifulSoup(html,"html.parser") #;print(bsObj)
# bsObj = BeautifulSoup(html,"html5lib") #;print(bsObj)
author = bsObj.find('span',{'class':'rich_media_meta rich_media_meta_nickname'})
author = author.a.text.strip()
title = bsObj.find('h2',{'class':'rich_media_title'})
title = title.text.strip()
p = {'author':author,'title':title}
# p['link'] = page
ml.debug(p)
return p
def ana_cd(albumlink):
'''Get album JSON data'''
ml = mylogger(logfile,get_funcname())
year = op_sel(albumlink)
albumid = albumlink.split('=')[-1]
ml.dbg(albumid)
url = f'http://{host}/api/album/{albumid}/'
html = op_simple(url,ran_header(agentref,host,org))[0]
# print(html)
jdata = BeautifulSoup(html,"html.parser").prettify()
ml.dbg(jdata)
adict = ana_json(jdata)
adict['year'] = year
ml.dbg(adict)
return adict
def ana_cd(albumlink):
'''Get album JSON data'''
# ml = mylogger(logfile,get_funcname())
# html = op_simple(albumlink,ran_header(ref=agentref))[0]
year = op_sel(albumlink)
# print(year)
albumid = albumlink.split('=')[-1]
# print(albumid)
url = f'http://music.163.com/api/album/{albumid}/'
html = op_simple(url, ran_header(ref=agentref))[0]
jdata = BeautifulSoup(html, "html.parser").prettify()
# jdata = bsObj.prettify()
adict = ana_json(jdata)
adict['year'] = year
# print(jdata)
return adict
def ana_wx(page):
'''Analyze Weixin web'''
ml = mylogger(logfile,get_funcname())
html = op_simple(page,ran_header())[0]
# print(html)
bsObj = BeautifulSoup(html,"html.parser") #;print(bsObj)
# bsObj = BeautifulSoup(html,"html5lib") #;print(bsObj)
try:
author = bsObj.find('span',{'class':'rich_media_meta rich_media_meta_nickname'})
author = author.a.text.strip()
title = bsObj.find('h2',{'class':'rich_media_title'})
title = title.text.strip()
p = {'author':author,'title':title}
# p['link'] = page
ml.dbg(p)
except:
return None
return p
def get_loc_cd(song_id):
l = mylogger(logfile,get_funcname())
url = 'http://www.xiami.com/widget/xml-single/sid/%s' % song_id
# url = url.replace('%s', song_id)
# url = 'file:///E://xml.xml'
page = op_simple(url)
l.debug(page[1])
bsObj = BeautifulSoup(page[0],"html.parser") #;print(bsObj)
location = bsObj.find("location")
location = str(location)[19:-14]
if location == '':
l.debug('Track not published')
SongDic = {}
else:
l.debug('Raw Location: '+location)
location = decry(location)
# location = location.replace('/m128','/m320')
song = bsObj.find("song_name")
song = modstr(str(song)[20:-15])
singer = bsObj.find("artist_name")
singer = modstr(str(singer)[22:-17])
SongDic = {'location':location,'song':song,'singer':singer}
l.debug(SongDic)
return SongDic
def test_op_simple(self):
print('Test op_simple')
url = 'http://www.xiami.com/widget/xml-single/sid/1769402049'
html = openlink.op_simple(url)
# print(url)
self.assertEqual(html[1], 200)