mirrors/irs
1
1
Fork 0
mirror of https://github.com/cooperhammond/irs.git synced 2024-12-22 17:35:28 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'master' into captcha-cheat

Browse source
This commit is contained in:
Kepoor Hampond 2017-09-30 18:06:03 -07:00 committed by GitHub
parent 18ae50b484 d21ac18059
commit 979201b66f
1 changed files with 64 additions and 27 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

91
irs/ripper.py
View file

@ -133,7 +133,7 @@ class Ripper:
return locations
def find_yt_url(self, song=None, artist=None, additional_search=None, caught_by_google=False):
def find_yt_url(self, song=None, artist=None, additional_search=None, caught_by_google=False, first=False):
if additional_search is None:
additional_search = Config.parse_search_terms(self)
print(str(self.args["hook-text"].get("youtube")))
@ -160,11 +160,14 @@ init, or in method arguments.")
soup = BeautifulSoup(CaptchaCheat.cheat_it(link), 'html.parser')
# print(soup.prettify())
# with open("index.html", "w") as f:
# f.write(soup.prettify().encode('utf-8'))
def find_link(link):
try:
if "yt-simple-endpoint style-scope ytd-video-renderer" in str(" ".join(link["class"])) or \
"yt-uix-tile-link yt-ui-ellipsis yt-ui-ellipsis-2 yt-uix-sessionlink spf-link" in str(" ".join(link["class"])):
"yt-uix-tile-link yt-ui-ellipsis yt-ui-ellipsis-2 yt-uix-sessionlink spf-link " in str(" ".join(link["class"])):
if "&list=" not in link["href"]:
return link
except KeyError:
@ -173,7 +176,7 @@ init, or in method arguments.")
results = list(filter(None, map(find_link, soup.find_all("a"))))
garbage_phrases = "cover album live clean rare version full full \
album".split(" ")
album row at @ session".split(" ")
self.code = None
counter = 0
@ -181,11 +184,14 @@ album".split(" ")
while self.code is None and counter <= 10:
counter += 1
for link in results:
if first == True:
self.code = link
break
if ObjManip.check_garbage_phrases(garbage_phrases,
link["title"], song):
continue
if ObjManip.blank_include(link["title"], song) and \
ObjManip.blank_include(link["title"], artist):
if ObjManip.check_garbage_phrases(garbage_phrases,
link["title"], song):
continue
self.code = link
break
@ -200,20 +206,33 @@ album".split(" ")
self.code = link
break
if self.code is None:
for link in results:
if ObjManip.check_garbage_phrases(garbage_phrases,
link["title"], song):
continue
if ObjManip.blank_include(link["title"], song):
self.code = link
break
if self.code is None:
song = ObjManip.limit_song_name(song)
if self.code is None:
if self.code is None and first is not True:
if additional_search == "lyrics":
return self.find_yt_url(song, artist, "")
return self.find_yt_url(song, artist, additional_search, caught_by_google, first)
try:
return ("https://youtube.com" + self.code["href"], self.code["title"])
except TypeError:
# Assuming Google catches you trying to search youtube for music ;)
return self.find_yt_url(song=song, artist=artist, additional_search=additional_search, caught_by_google=True)
if caught_by_google is not True:
# Assuming Google catches you trying to search youtube for music ;)
print("Trying to bypass google captcha.")
return self.find_yt_url(song=song, artist=artist, additional_search=additional_search, caught_by_google=True)
elif caught_by_google is True and first is not True:
return self.find_yt_url(song, artist, additional_search, caught_by_google, first=True)
def album(self, title, artist=None): # Alias for spotify_list("album", ..)
return self.spotify_list("album", title=title, artist=artist)
@ -252,20 +271,37 @@ with init, or in method arguments.")
if len(list_of_lists) > 0:
the_list = None
for list_ in list_of_lists:
if ObjManip.blank_include(list_["name"], title):
if Config.parse_artist(self):
if ObjManip.blank_include(list_["artists"][0]["name"],
Config.parse_artist(self)):
the_list = self.spotify.album(list_["uri"])
break
else:
if type == "album":
the_list = self.spotify.album(list_["uri"])
if Config.parse_exact(self) == True:
if list_["name"].encode("utf-8") == title.encode("utf-8"):
if Config.parse_artist(self):
if list_["artists"][0]["name"].encode("utf-8") == \
Config.parse_artist(self).encode('utf-8'):
the_list = self.spotify.album(list_["uri"])
break
else:
the_list = self.spotify.user_playlist(
list_["owner"]["id"], list_["uri"])
the_list["artists"] = [{"name": username}]
break
if type == "album":
the_list = self.spotify.album(list_["uri"])
else:
the_list = self.spotify.user_playlist(
list_["owner"]["id"], list_["uri"])
the_list["artists"] = [{"name": username}]
break
else:
if ObjManip.blank_include(list_["name"], title):
if Config.parse_artist(self):
if ObjManip.blank_include(list_["artists"][0]["name"],
Config.parse_artist(self)):
the_list = self.spotify.album(list_["uri"])
break
else:
if type == "album":
the_list = self.spotify.album(list_["uri"])
else:
the_list = self.spotify.user_playlist(
list_["owner"]["id"], list_["uri"])
the_list["artists"] = [{"name": username}]
break
if the_list is not None:
YdlUtils.clear_line()
@ -397,7 +433,6 @@ init, or in method arguments.")
print(self.args["hook-text"].get("song").format(song, artist))
file_name = data["file_prefix"] + ObjManip.blank(song, False) + ".mp3"
ydl_opts = {
'format': 'bestaudio/best',
'postprocessors': [{
@ -409,9 +444,11 @@ init, or in method arguments.")
'progress_hooks': [YdlUtils.my_hook],
'output': "tmp_file",
'prefer-ffmpeg': True,
'ffmpeg_location': os.path.expanduser("~/.irs/bin/")
}
if Config.check_ffmpeg() is False:
ydl_opts.update({'ffmpeg_location': os.path.expanduser("~/.irs/bin/")})
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
ydl.download([video_url])