mcvsoftware/music-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixed zaycev.net extractor

Browse Source
This commit is contained in:
Manuel Cortez 2018-12-28 19:46:26 -06:00
parent 2f4416f6bb
commit 130fb40d78
1 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
src/extractors/zaycev.py
View File

@ -19,23 +19,23 @@ class interface(object):
log.debug("Started extraction service for zaycev.net") log.debug("Started extraction service for zaycev.net")
def search(self, text, page=1): def search(self, text, page=1):
site = 'http://go.mail.ru/zaycev?q=%s&page=%s' % (text, page) site = "http://zaycev.net/search.html?query_search=%s" % (text,)
log.debug("Retrieving data from {0}...".format(site,)) log.debug("Retrieving data from {0}...".format(site,))
r = requests.get(site) r = requests.get(site)
soup = BeautifulSoup(r.text, 'html.parser') soup = BeautifulSoup(r.text, 'html.parser')
D = r'длительность.(\d+\:\d+\:\d+)' search_results = soup.find_all("div", {"class": "musicset-track__title track-geo__title"})
R = r'размер.((\d+|\d+.\d+) \w+)'
B = r'битрейт.(\d+ \w+)'
self.dh = [[x.get_text(), x.get('href')]for x in soup.find_all('a', {'class': "light-link"}) if x.get_text() != "Читать далее"]
self.hd = [{'duration': re.search(D, str(x)).group()[13:], 'size': re.search(R, str(x)).group()[7:], 'bitrate': re.search(B, str(x)).group()[8:]} for x in soup.find_all('div', {'class': "result__snp"})]
self.results = [] self.results = []
for i in range(len(self.hd)): for i in search_results:
# The easiest method to get artist and song names is to fetch links. There are only two links per result here.
data = i.find_all("a")
# from here, data[0] contains artist info and data[1] contains info of the retrieved song.
s = baseFile.song(self) s = baseFile.song(self)
s.title = self.dh[i][0] s.title = data[1].text
s.url = self.dh[i][1] s.artist = data[0].text
s.duration = self.hd[i]["duration"] s.url = "http://zaycev.net%s" % (data[1].attrs["href"])
s.size = self.hd[i]["size"] # s.duration = self.hd[i]["duration"]
s.bitrate = self.hd[i]["bitrate"] # s.size = self.hd[i]["size"]
# s.bitrate = self.hd[i]["bitrate"]
self.results.append(s) self.results.append(s)
log.debug("{0} results found.".format(len(self.results))) log.debug("{0} results found.".format(len(self.results)))