mandos.search.chembl.ChemblScrapeSearch._scrape() - Code Metrics - Inspection of "feat: no clue" - dmyersturnbull/mandos - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — main ( ec3fe3...82dd22 )

by Douglas

created 2021-08-02 23:37 UTC

mandos.search.chembl.ChemblScrapeSearch._scrape() A

↳ Parent: mandos.search.chembl

Complexity

Conditions

Size

Total Lines	20
Code Lines	18

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	4
eloc	18
nop	2
dl	0
loc	20
rs	9.5
c	0
b	0
f	0

import abc

from typing import TypeVar

from typeddfs import TypedDfs


from mandos.model.settings import QUERY_EXECUTORS

from mandos.model.scrape import Scraper, By
from mandos.model.apis.chembl_api import ChemblApi
from mandos.model.hits import AbstractHit
from mandos.model.searches import Search

H = TypeVar("H", bound=AbstractHit, covariant=True)



class _ScraperSingleton:
    x = None

    @classmethod
    def get(cls):

        if cls.x is None:
            cls.x = Scraper.create(QUERY_EXECUTORS.chembl)
        return cls.x


ChemblTable = TypedDfs.typed("ChemblTable").build()


class ChemblScrapeSearch(Search[H], metaclass=abc.ABCMeta):

    """"""

    @classmethod
    def _page_name(cls) -> str:
        raise NotImplementedError()

    def _scrape(self, chembl_id: int) -> ChemblTable:
        # e.g. target_predictions
        url = f"https://www.ebi.ac.uk/chembl/embed/#compound_report_card/{chembl_id}/{self._page_name}"

        scraper = _ScraperSingleton.get()
        scraper.go(url)
        rows = []
        i = 2
        while True:
            table = scraper.find_element("table", By.TAG_NAME)
            for tr in table.find_elements("tr"):

                rows += [td.text for td in tr.find_elements("td")]
            # noinspection PyBroadException
            try:
                scraper.find_elements(str(i), By.LINK_TEXT)
            except Exception:

                break
            i += 1
        header = rows[0]
        rows = rows[1:]
        return ChemblTable(rows, columns=header)


class ChemblSearch(Search[H], metaclass=abc.ABCMeta):

    def __init__(self, key: str, api: ChemblApi):
        """
        Constructor.

        Args:
            api:
        """
        super().__init__(key)
        self.api = api


__all__ = ["ChemblSearch", "ChemblScrapeSearch", "ChemblTable"]


1			import abc
			0 ignored issues – show introduced 2021-03-10 02:41 UTC by Report Bug Copy Issue Report Missing module docstring Loading history...
2			from typing import TypeVar
3
4			from typeddfs import TypedDfs
			0 ignored issues – show introduced 2021-08-02 23:39 UTC by Report Bug Copy Issue Report Unable to import 'typeddfs' Loading history...
5
6			from mandos.model.settings import QUERY_EXECUTORS
7
8			from mandos.model.scrape import Scraper, By
9			from mandos.model.apis.chembl_api import ChemblApi
10			from mandos.model.hits import AbstractHit
11			from mandos.model.searches import Search
12
13			H = TypeVar("H", bound=AbstractHit, covariant=True)
			0 ignored issues – show Coding Style Naming introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Class name "H" doesn't conform to PascalCase naming style ('[^\\W\\da-z][^\\W_]+$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
14
15
16			class _ScraperSingleton:
17			x = None
18
19			@classmethod
20			def get(cls):
			0 ignored issues – show introduced 2021-08-02 23:39 UTC by Report Bug Copy Issue Report Missing function or method docstring Loading history...
21			if cls.x is None:
22			cls.x = Scraper.create(QUERY_EXECUTORS.chembl)
23			return cls.x
24
25
26			ChemblTable = TypedDfs.typed("ChemblTable").build()
27
28
29			class ChemblScrapeSearch(Search[H], metaclass=abc.ABCMeta):
			0 ignored issues – show Documentation introduced 2021-01-25 23:06 UTC by Report Bug Copy Issue Report Empty class docstring Loading history...
30			""""""
31
32			@classmethod
33			def _page_name(cls) -> str:
34			raise NotImplementedError()
35
36			def _scrape(self, chembl_id: int) -> ChemblTable:
37			# e.g. target_predictions
38			url = f"https://www.ebi.ac.uk/chembl/embed/#compound_report_card/{chembl_id}/{self._page_name}"
			0 ignored issues – show Coding Style introduced 2021-08-02 23:39 UTC by Report Bug Copy Issue Report This line is too long as per the coding-style (103/100). This check looks for lines that are too long. You can specify the maximum line length. Loading history...
39			scraper = _ScraperSingleton.get()
40			scraper.go(url)
41			rows = []
42			i = 2
43			while True:
44			table = scraper.find_element("table", By.TAG_NAME)
45			for tr in table.find_elements("tr"):
			0 ignored issues – show Coding Style Naming introduced 2021-08-02 23:39 UTC by Report Bug Copy Issue Report Variable name "tr" doesn't conform to snake_case naming style ('([^\\W\\dA-Z][^\\WA-Z]2,\|_[^\\WA-Z]*\|__[^\\WA-Z\\d_][^\\WA-Z]+__)$' pattern) This check looks for invalid names for a range of different identifiers. You can set regular expressions to which the identifiers must conform if the defaults do not match your requirements. If your project includes a Pylint configuration file, the settings contained in that file take precedence. To find out more about Pylint, please refer to their site. Loading history...
46			rows += [td.text for td in tr.find_elements("td")]
47			# noinspection PyBroadException
48			try:
49			scraper.find_elements(str(i), By.LINK_TEXT)
50			except Exception:
			0 ignored issues – show Best Practice introduced 2021-08-02 23:39 UTC by Report Bug Copy Issue Report Catching very general exceptions such as `Exception` is usually not recommended. Generally, you would want to handle very specific errors in the exception handler. This ensure that you do not hide other types of errors which should be fixed. So, unless you specifically plan to handle any error, consider adding a more specific exception. Loading history...
51			break
52			i += 1
53			header = rows[0]
54			rows = rows[1:]
55			return ChemblTable(rows, columns=header)
56
57
58			class ChemblSearch(Search[H], metaclass=abc.ABCMeta):
			0 ignored issues – show introduced 2021-03-10 02:41 UTC by Report Bug Copy Issue Report Missing class docstring Loading history...
59			def __init__(self, key: str, api: ChemblApi):
60			"""
61			Constructor.
62
63			Args:
64			api:
65			"""
66			super().__init__(key)
67			self.api = api
68
69
70			__all__ = ["ChemblSearch", "ChemblScrapeSearch", "ChemblTable"]
71

dmyersturnbull / mandos

Push — main ( ec3fe3...82dd22 )

mandos.search.chembl.ChemblScrapeSearch._scrape() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like