titlesearch.mal.mal.MyAnimeList.group_titles() - Code Metrics - DaRealFreak/TitleSearch - Measure and Improve Code Quality continuously with Scrutinizer

titlesearch.mal.mal.MyAnimeList.group_titles() F
last analyzed 2018-04-07 14:58 UTC

↳ Parent: titlesearch.mal.mal

Complexity

Conditions

Size

Total Lines	28
Code Lines	18

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
eloc	18
dl	0
loc	28
rs	3.1304
c	0
b	0
f	0
cc	10
nop	2

How to fix Complexity

#!/usr/local/bin/python
class SomeClass:
    def some_method(self):
        """Do x and return foo."""
# coding: utf-8

import re

import bs4
import jellyfish
import requests
from bs4 import BeautifulSoup as Soup


from titlesearch.language.language_settings import *



class MyAnimeList(object):

    """Module for extracting alternative language titles for titles from mangaupdates.com"""

    SEARCH_URL = 'https://myanimelist.net/search/all'
    KNOWN_LANGUAGES = [English, Japanese]

    ADDED_KEYWORDS = [' (Novel)']
    MAPPING = {
        'English:': 'english',
        'Synonyms:': 'english',
        'Japanese:': 'japanese'
    }

    @staticmethod
    def get_similar_titles(title: str) -> list:
        """Main function for extracting alternate titles

        :type title: str
        :return:
        """
        payload = {
            'q': title
        }

        results = []

        link = requests.get(url=MyAnimeList.SEARCH_URL, params=payload)
        # html5lib parser since html.parser will fail at the content-left div already
        soup = Soup(link.text, 'html5lib')
        for search_result in soup.select('div.content-left div.list.di-t.w100 a.hoverinfo_trigger'):
            search_group = re.search('/anime/|/manga/', search_result['href'])
            if search_result.text.strip() and search_group:
                results.append({
                    'title': search_result.text.strip(),
                    'link': search_result['href'],
                    'similarity': jellyfish.jaro_distance(search_result.text.strip().lower(), title.lower())

                })

        results.sort(key=lambda item: item['similarity'], reverse=True)
        return results

    @staticmethod
    def get_alternative_titles(title: str = '', link: str = '') -> dict:
        """Get alternative titles for the given title. Preferring link over title argument

        :type title: str
        :type link: str
        :return:
        """
        if title and not link:
            link = MyAnimeList.get_similar_titles(title)
            if link:
                link = link[0]['link']
            else:
                return MyAnimeList.group_titles(title, None)

        link = requests.get(url=link)
        soup = Soup(link.text, 'html5lib')

        release_title = soup.find('span', attrs={'itemprop': 'name'})
        if release_title:
            release_title = release_title.text
        else:
            release_title = title if title else ''

        return MyAnimeList.group_titles(release_title=release_title, soup=soup)

    @staticmethod
    def group_titles(release_title: str, soup) -> dict:
        """Extract and group the titles of the bs4 Tag to their respective language

        :type release_title: str
        :type soup: bs4.element.Tag|None
        :return:
        """
        grouped_titles = {}
        for language in MyAnimeList.KNOWN_LANGUAGES:
            grouped_titles[language.__name__.lower()] = []

        grouped_titles['english'] = [release_title]

        if soup:
            for search_result in soup.find_all('div', attrs={'class': 'spaceit_pad'}):  # type:
                category = search_result.find('span', attrs={'class': 'dark_text'})
                if category:
                    value = "".join(
                        [t for t in search_result.contents if isinstance(t, bs4.element.NavigableString)]).strip()

                    if category.text.strip() == 'Synonyms:':
                        for synonym in value.split(', '):
                            grouped_titles[MyAnimeList.MAPPING[category.text]].append(synonym)
                    else:
                        if category.text.strip() in MyAnimeList.MAPPING:
                            grouped_titles[MyAnimeList.MAPPING[category.text.strip()]].append(value)

        return grouped_titles


1			#!/usr/local/bin/python
			0 ignored issues – show Coding Style introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report This module should have a docstring. The coding style of this project requires that you add a docstring to this code element. Below, you find an example for methods: class SomeClass: def some_method(self): """Do x and return foo.""" If you would like to know more about docstrings, we recommend to read PEP-257: Docstring Conventions. Loading history...
2			# coding: utf-8
3
4			import re
5
6			import bs4
7			import jellyfish
8			import requests
9			from bs4 import BeautifulSoup as Soup
			0 ignored issues – show introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report Imports from package bs4 are not grouped Loading history...
10
11			from titlesearch.language.language_settings import *
			0 ignored issues – show Coding Style introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report The usage of wildcard imports like `titlesearch.language.language_settings` should generally be avoided. Loading history... Unused Code introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report `np` was imported with wildcard, but is not used. Loading history... Unused Code introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report `Korean` was imported with wildcard, but is not used. Loading history... Unused Code introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report `LanguageTemplate` was imported with wildcard, but is not used. Loading history...
12
13
14			class MyAnimeList(object):
			0 ignored issues – show Unused Code introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report The variable `__class__` seems to be unused. Loading history...
15			"""Module for extracting alternative language titles for titles from mangaupdates.com"""
16
17			SEARCH_URL = 'https://myanimelist.net/search/all'
18			KNOWN_LANGUAGES = [English, Japanese]
			0 ignored issues – show Comprehensibility Best Practice introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report The variable `Japanese` does not seem to be defined. Loading history... Comprehensibility Best Practice introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report The variable `English` does not seem to be defined. Loading history...
19			ADDED_KEYWORDS = [' (Novel)']
20			MAPPING = {
21			'English:': 'english',
22			'Synonyms:': 'english',
23			'Japanese:': 'japanese'
24			}
25
26			@staticmethod
27			def get_similar_titles(title: str) -> list:
28			"""Main function for extracting alternate titles
29
30			:type title: str
31			:return:
32			"""
33			payload = {
34			'q': title
35			}
36
37			results = []
38
39			link = requests.get(url=MyAnimeList.SEARCH_URL, params=payload)
40			# html5lib parser since html.parser will fail at the content-left div already
41			soup = Soup(link.text, 'html5lib')
42			for search_result in soup.select('div.content-left div.list.di-t.w100 a.hoverinfo_trigger'):
43			search_group = re.search('/anime/\|/manga/', search_result['href'])
44			if search_result.text.strip() and search_group:
45			results.append({
46			'title': search_result.text.strip(),
47			'link': search_result['href'],
48			'similarity': jellyfish.jaro_distance(search_result.text.strip().lower(), title.lower())
			0 ignored issues – show Coding Style introduced 2018-04-05 10:05 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (108/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
49			})
50
51			results.sort(key=lambda item: item['similarity'], reverse=True)
52			return results
53
54			@staticmethod
55			def get_alternative_titles(title: str = '', link: str = '') -> dict:
56			"""Get alternative titles for the given title. Preferring link over title argument
57
58			:type title: str
59			:type link: str
60			:return:
61			"""
62			if title and not link:
63			link = MyAnimeList.get_similar_titles(title)
64			if link:
65			link = link[0]['link']
66			else:
67			return MyAnimeList.group_titles(title, None)
68
69			link = requests.get(url=link)
70			soup = Soup(link.text, 'html5lib')
71
72			release_title = soup.find('span', attrs={'itemprop': 'name'})
73			if release_title:
74			release_title = release_title.text
75			else:
76			release_title = title if title else ''
77
78			return MyAnimeList.group_titles(release_title=release_title, soup=soup)
79
80			@staticmethod
81			def group_titles(release_title: str, soup) -> dict:
82			"""Extract and group the titles of the bs4 Tag to their respective language
83
84			:type release_title: str
85			:type soup: bs4.element.Tag\|None
86			:return:
87			"""
88			grouped_titles = {}
89			for language in MyAnimeList.KNOWN_LANGUAGES:
90			grouped_titles[language.__name__.lower()] = []
91
92			grouped_titles['english'] = [release_title]
93
94			if soup:
95			for search_result in soup.find_all('div', attrs={'class': 'spaceit_pad'}): # type:
96			category = search_result.find('span', attrs={'class': 'dark_text'})
97			if category:
98			value = "".join(
99			[t for t in search_result.contents if isinstance(t, bs4.element.NavigableString)]).strip()
			0 ignored issues – show Coding Style introduced 2018-04-07 14:58 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (114/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
100			if category.text.strip() == 'Synonyms:':
101			for synonym in value.split(', '):
102			grouped_titles[MyAnimeList.MAPPING[category.text]].append(synonym)
103			else:
104			if category.text.strip() in MyAnimeList.MAPPING:
105			grouped_titles[MyAnimeList.MAPPING[category.text.strip()]].append(value)
106
107			return grouped_titles
108

DaRealFreak / TitleSearch

titlesearch.mal.mal.MyAnimeList.group_titles() F last analyzed 2018-04-07 14:58 UTC

Complexity

Size

Duplication

Importance

How to fix Complexity

Complexity

Duplication Side-by-Side

Filter issues like

titlesearch.mal.mal.MyAnimeList.group_titles() F
last analyzed 2018-04-07 14:58 UTC