From e16d226be262c2c89daaff648e4090b6f4ff3696 Mon Sep 17 00:00:00 2001
From: Jirka <vrbka.jirka@gmail.com>
Date: Sun, 17 Nov 2019 21:03:39 +0100
Subject: [PATCH] Clean unused code
---
src/scraper/scraper.py | 104 +----------------------------------------
1 file changed, 2 insertions(+), 102 deletions(-)
diff --git a/src/scraper/scraper.py b/src/scraper/scraper.py
index 0b5bd4d..18ec3ae 100644
--- a/src/scraper/scraper.py
+++ b/src/scraper/scraper.py
@@ -1,61 +1,11 @@
from __future__ import annotations
import re
-from typing import List, Dict
-from bs4 import BeautifulSoup, NavigableString
+from bs4 import BeautifulSoup
import requests
-class ScraperBodyGet:
- def __init__(self, soup: BeautifulSoup):
- self.soup = soup
-
- def get_attribute_value(self, attribute: str):
- return self.soup[attribute]
-
- def get_text(self):
- return self.soup.get_text()
-
- def also(self):
- return ScraperBodyInit(soup=self.soup)
-
-
-class ScraperBodyInit:
- soup: BeautifulSoup
- element_name: str = None
- element_attribute: (str, str) = None
-
- def __init__(self, soup: BeautifulSoup):
- self.soup = soup
-
- def at_element(self, name_of_element: str) -> ScraperBodyInit:
- self.element_name = name_of_element
- return self
-
- def with_attribute_having_value(self, attribute: str, value: str) -> ScraperBodyInit:
- self.element_attribute = (attribute, value)
- return self
-
- def with_attribute_having_values(self, attribute: str, values: List[str]) -> List[(str, ScraperBodyInit)]:
- results = []
- for value in values:
- s = ScraperBodyInit(self.soup)
- s.at_element(self.element_name)
- s.with_attribute_having_value(attribute, value)
- results.append((value, s))
- return results
-
- def find(self):
- attrs = {self.element_attribute[0]: self.element_attribute[1]}
- new_soup = self.soup.find(self.element_name, attrs)
- return ScraperBodyGet(new_soup)
-
- def reset(self) -> None:
- self.element_name = None
- self.element_attribute = None
-
-
class Element:
_soup: BeautifulSoup
@@ -81,6 +31,7 @@ class Element:
if self._soup is None:
return None
+ from bs4 import NavigableString
if isinstance(self._soup, NavigableString):
return self._soup
@@ -106,57 +57,6 @@ class Page:
return Element(BeautifulSoup(self._page.content, "html.parser"))
-class Then:
- _soup: BeautifulSoup
- _status_code: int
-
- def __init__(self, soup: BeautifulSoup, status_code: int):
- self._soup = soup
- self._status_code = status_code
-
- def get_status_code(self):
- return self._status_code
-
- def get_attribute(self, attribute: str):
- return None if self._soup is None else self._soup[attribute]
-
- def get_text(self):
- return None if self._soup is None else self._soup.get_text()
-
-
-class When:
- _soup: BeautifulSoup
- _status_code: int
-
- def __init__(self, soup: BeautifulSoup, status_code: int):
- self._soup = soup
- self._status_code = status_code
-
- def id(self, id: str) -> When:
- self._soup = self._soup.find(id=id)
- return self
-
- def attribute(self, attribute: str, value: str = None) -> When:
- self._soup = self._soup.find(attrs={attribute: value})
- return self
-
- def Then(self):
- return Then(self._soup, self._status_code)
-
-
-class Given:
- _request: requests.api
-
- def __init__(self, url: str):
- self._request = requests.get(url=url)
-
- def status_code(self) -> int:
- return self._request.status_code
-
- def When(self):
- return When(BeautifulSoup(self._request.content, "html.parser"))
-
-
class Scraper:
@staticmethod
def at(web: str) -> ScraperBodyInit:
--
GitLab