- Notifications
You must be signed in to change notification settings - Fork 46.7k
/
Copy pathfetch_anime_and_play.py
188 lines (138 loc) · 5.67 KB
/
fetch_anime_and_play.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
importrequests
frombs4importBeautifulSoup, NavigableString, Tag
fromfake_useragentimportUserAgent
BASE_URL="https://ww1.gogoanime2.org"
defsearch_scraper(anime_name: str) ->list:
"""[summary]
Take an url and
return list of anime after scraping the site.
>>> type(search_scraper("demon_slayer"))
<class 'list'>
Args:
anime_name (str): [Name of anime]
Raises:
e: [Raises exception on failure]
Returns:
[list]: [List of animes]
"""
# concat the name to form the search url.
search_url=f"{BASE_URL}/search/{anime_name}"
response=requests.get(
search_url, headers={"UserAgent": UserAgent().chrome}, timeout=10
) # request the url.
# Is the response ok?
response.raise_for_status()
# parse with soup.
soup=BeautifulSoup(response.text, "html.parser")
# get list of anime
anime_ul=soup.find("ul", {"class": "items"})
ifanime_ulisNoneorisinstance(anime_ul, NavigableString):
msg=f"Could not find and anime with name {anime_name}"
raiseValueError(msg)
anime_li=anime_ul.children
# for each anime, insert to list. the name and url.
anime_list= []
foranimeinanime_li:
ifisinstance(anime, Tag):
anime_url=anime.find("a")
ifanime_urlisNoneorisinstance(anime_url, NavigableString):
continue
anime_title=anime.find("a")
ifanime_titleisNoneorisinstance(anime_title, NavigableString):
continue
anime_list.append({"title": anime_title["title"], "url": anime_url["href"]})
returnanime_list
defsearch_anime_episode_list(episode_endpoint: str) ->list:
"""[summary]
Take an url and
return list of episodes after scraping the site
for an url.
>>> type(search_anime_episode_list("/anime/kimetsu-no-yaiba"))
<class 'list'>
Args:
episode_endpoint (str): [Endpoint of episode]
Raises:
e: [description]
Returns:
[list]: [List of episodes]
"""
request_url=f"{BASE_URL}{episode_endpoint}"
response=requests.get(
url=request_url, headers={"UserAgent": UserAgent().chrome}, timeout=10
)
response.raise_for_status()
soup=BeautifulSoup(response.text, "html.parser")
# With this id. get the episode list.
episode_page_ul=soup.find("ul", {"id": "episode_related"})
ifepisode_page_ulisNoneorisinstance(episode_page_ul, NavigableString):
msg=f"Could not find any anime eposiodes with name {anime_name}"
raiseValueError(msg)
episode_page_li=episode_page_ul.children
episode_list= []
forepisodeinepisode_page_li:
ifisinstance(episode, Tag):
url=episode.find("a")
ifurlisNoneorisinstance(url, NavigableString):
continue
title=episode.find("div", {"class": "name"})
iftitleisNoneorisinstance(title, NavigableString):
continue
episode_list.append(
{"title": title.text.replace(" ", ""), "url": url["href"]}
)
returnepisode_list
defget_anime_episode(episode_endpoint: str) ->list:
"""[summary]
Get click url and download url from episode url
>>> type(get_anime_episode("/watch/kimetsu-no-yaiba/1"))
<class 'list'>
Args:
episode_endpoint (str): [Endpoint of episode]
Raises:
e: [description]
Returns:
[list]: [List of download and watch url]
"""
episode_page_url=f"{BASE_URL}{episode_endpoint}"
response=requests.get(
url=episode_page_url, headers={"User-Agent": UserAgent().chrome}, timeout=10
)
response.raise_for_status()
soup=BeautifulSoup(response.text, "html.parser")
url=soup.find("iframe", {"id": "playerframe"})
ifurlisNoneorisinstance(url, NavigableString):
msg=f"Could not find url and download url from {episode_endpoint}"
raiseRuntimeError(msg)
episode_url=url["src"]
ifnotisinstance(episode_url, str):
msg=f"Could not find url and download url from {episode_endpoint}"
raiseRuntimeError(msg)
download_url=episode_url.replace("/embed/", "/playlist/") +".m3u8"
return [f"{BASE_URL}{episode_url}", f"{BASE_URL}{download_url}"]
if__name__=="__main__":
anime_name=input("Enter anime name: ").strip()
anime_list=search_scraper(anime_name)
print("\n")
iflen(anime_list) ==0:
print("No anime found with this name")
else:
print(f"Found {len(anime_list)} results: ")
fori, animeinenumerate(anime_list):
anime_title=anime["title"]
print(f"{i+1}. {anime_title}")
anime_choice=int(input("\nPlease choose from the following list: ").strip())
chosen_anime=anime_list[anime_choice-1]
print(f"You chose {chosen_anime['title']}. Searching for episodes...")
episode_list=search_anime_episode_list(chosen_anime["url"])
iflen(episode_list) ==0:
print("No episode found for this anime")
else:
print(f"Found {len(episode_list)} results: ")
fori, episodeinenumerate(episode_list):
print(f"{i+1}. {episode['title']}")
episode_choice=int(input("\nChoose an episode by serial no: ").strip())
chosen_episode=episode_list[episode_choice-1]
print(f"You chose {chosen_episode['title']}. Searching...")
episode_url, download_url=get_anime_episode(chosen_episode["url"])
print(f"\nTo watch, ctrl+click on {episode_url}.")
print(f"To download, ctrl+click on {download_url}.")