|
1
|
|
|
#!/usr/local/bin/python |
|
|
|
|
|
|
2
|
|
|
# coding: utf-8 |
|
3
|
|
|
|
|
4
|
|
|
import re |
|
5
|
|
|
from typing import Tuple |
|
6
|
|
|
|
|
7
|
|
|
import jellyfish |
|
8
|
|
|
import requests |
|
9
|
|
|
from bs4 import BeautifulSoup as Soup |
|
10
|
|
|
|
|
11
|
|
|
from titlesearch.language.detection import matches_language |
|
12
|
|
|
from titlesearch.language.language_settings import * |
|
|
|
|
|
|
13
|
|
|
|
|
14
|
|
|
|
|
15
|
|
|
class BakaUpdates(object): |
|
|
|
|
|
|
16
|
|
|
"""Module for extracting alternative language titles for titles from https://www.mangaupdates.com""" |
|
|
|
|
|
|
17
|
|
|
|
|
18
|
|
|
SEARCH_URL = 'https://www.mangaupdates.com/series.html' |
|
19
|
|
|
KNOWN_LANGUAGES = [English, Japanese, Korean] |
|
|
|
|
|
|
20
|
|
|
ADDED_KEYWORDS = [' (Novel)'] |
|
21
|
|
|
|
|
22
|
|
|
@staticmethod |
|
23
|
|
|
def get_similar_titles(title: str) -> list: |
|
24
|
|
|
"""Main function for extracting alternate titles |
|
25
|
|
|
|
|
26
|
|
|
:type title: str |
|
27
|
|
|
:return: |
|
28
|
|
|
""" |
|
29
|
|
|
payload = { |
|
30
|
|
|
'stype': 'title', |
|
31
|
|
|
'search': title |
|
32
|
|
|
} |
|
33
|
|
|
|
|
34
|
|
|
link = requests.get(url=BakaUpdates.SEARCH_URL, params=payload) |
|
35
|
|
|
soup = Soup(link.text, 'html.parser') |
|
36
|
|
|
|
|
37
|
|
|
seen_titles = [] |
|
38
|
|
|
results = [] |
|
39
|
|
|
for s in soup.find_all('td', attrs={"class": "text pad col1"}): |
|
|
|
|
|
|
40
|
|
|
search_result = BakaUpdates.clean_title(s.text) |
|
41
|
|
|
# I decided to add a seen titles list to prevent duplicate titles in the output. |
|
42
|
|
|
# BakaUpdates search returns titles without the added keywords first, so I'll skip the second result |
|
|
|
|
|
|
43
|
|
|
# which is most likely a novel |
|
44
|
|
|
if search_result not in seen_titles: |
|
45
|
|
|
results.append({ |
|
46
|
|
|
'title': search_result, |
|
47
|
|
|
'link': s.find_next('a', href=True)['href'], |
|
48
|
|
|
'similarity': jellyfish.jaro_distance(search_result.lower(), title.lower()) |
|
49
|
|
|
}) |
|
50
|
|
|
seen_titles.append(search_result) |
|
51
|
|
|
|
|
52
|
|
|
results.sort(key=lambda item: item['similarity'], reverse=True) |
|
53
|
|
|
return results |
|
54
|
|
|
|
|
55
|
|
|
@staticmethod |
|
56
|
|
|
def get_alternative_titles(title: str = '', link: str = '') -> dict: |
|
57
|
|
|
"""Get alternative titles for the given title. Preferring link over title argument |
|
58
|
|
|
|
|
59
|
|
|
:type title: str |
|
60
|
|
|
:type link: str |
|
61
|
|
|
:return: |
|
62
|
|
|
""" |
|
63
|
|
|
if title and not link: |
|
64
|
|
|
link = BakaUpdates.get_similar_titles(title) |
|
65
|
|
|
if link: |
|
66
|
|
|
link = link[0]['link'] |
|
67
|
|
|
else: |
|
68
|
|
|
return BakaUpdates.group_titles(title, []) |
|
69
|
|
|
|
|
70
|
|
|
link = requests.get(url=link) |
|
71
|
|
|
release_title, alternative_titles = BakaUpdates.extract_titles(link.text) |
|
72
|
|
|
return BakaUpdates.group_titles(release_title, alternative_titles) |
|
73
|
|
|
|
|
74
|
|
|
@staticmethod |
|
75
|
|
|
def extract_titles(html_content: str) -> Tuple[str, list]: |
|
76
|
|
|
"""Extract the titles from the HTML DOM tree |
|
77
|
|
|
|
|
78
|
|
|
:type html_content: str |
|
79
|
|
|
:return: |
|
80
|
|
|
""" |
|
81
|
|
|
# html.parser can't handle <br> tags instead of <br/> tags and will append all titles as child |
|
|
|
|
|
|
82
|
|
|
# to the previous title, html5lib is slower but works properly |
|
83
|
|
|
soup = Soup(html_content, 'html5lib') |
|
84
|
|
|
|
|
85
|
|
|
release_title = soup.find('span', attrs={'class': ['releasestitle', 'tabletitle']}).text |
|
86
|
|
|
associated_names_tag = soup.find('b', string=re.compile("Associated Names")) |
|
87
|
|
|
alternative_titles = associated_names_tag.parent.find_next_sibling('div', attrs={'class': 'sContent'}) |
|
|
|
|
|
|
88
|
|
|
for br in alternative_titles.find_all("br"): |
|
|
|
|
|
|
89
|
|
|
br.replace_with("\n") |
|
90
|
|
|
alternative_titles = [BakaUpdates.clean_title(title) for title in alternative_titles.text.split('\n') |
|
|
|
|
|
|
91
|
|
|
if title.strip()] |
|
92
|
|
|
|
|
93
|
|
|
return release_title, alternative_titles |
|
94
|
|
|
|
|
95
|
|
View Code Duplication |
@staticmethod |
|
|
|
|
|
|
96
|
|
|
def group_titles(release_title: str, alternative_titles: list) -> dict: |
|
97
|
|
|
"""Iterate through the supported languages and group the titles according to the detected languages |
|
|
|
|
|
|
98
|
|
|
|
|
99
|
|
|
:type release_title: str |
|
100
|
|
|
:type alternative_titles: str |
|
101
|
|
|
:return: |
|
102
|
|
|
""" |
|
103
|
|
|
grouped_titles = {} |
|
104
|
|
|
for language in BakaUpdates.KNOWN_LANGUAGES: |
|
105
|
|
|
grouped_titles[language.__name__.lower()] = [] |
|
106
|
|
|
|
|
107
|
|
|
grouped_titles['english'] = [release_title] |
|
108
|
|
|
|
|
109
|
|
|
for title in alternative_titles: |
|
110
|
|
|
for language in BakaUpdates.KNOWN_LANGUAGES: |
|
111
|
|
|
if matches_language(title, language) and title not in grouped_titles[language.__name__.lower()]: |
|
|
|
|
|
|
112
|
|
|
grouped_titles[language.__name__.lower()].append(title) |
|
113
|
|
|
continue |
|
114
|
|
|
|
|
115
|
|
|
return grouped_titles |
|
116
|
|
|
|
|
117
|
|
|
@staticmethod |
|
118
|
|
|
def clean_title(title: str) -> str: |
|
119
|
|
|
"""Strip title from leftover spaces and remove keywords added by BakaUpdates |
|
120
|
|
|
|
|
121
|
|
|
:type title: str |
|
122
|
|
|
:return: |
|
123
|
|
|
""" |
|
124
|
|
|
title = title.strip() |
|
125
|
|
|
for keyword in BakaUpdates.ADDED_KEYWORDS: |
|
126
|
|
|
title = title.replace(keyword, '') |
|
127
|
|
|
return title |
|
128
|
|
|
|
DaRealFreak /
TitleSearch
Loading history...
The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods:
If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions.