kennethreitz/requests-html
1
0
Fork 0
mirror of https://github.com/kennethreitz/requests-html.git synced 2026-06-05 23:00:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

vast improvements

Browse Source 
Signed-off-by: Kenneth Reitz <me@kennethreitz.org>
This commit is contained in:
Kenneth Reitz
2018-03-03 08:17:42 -05:00
parent 7a1466c943
commit 8af172c5ce
2 changed files with 14 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
requests_html.py
+13 -4
View File
@@ -7,6 +7,7 @@ from typing import Set, Union, List, MutableMapping, Optional
import pyppeteer
import requests
from pyquery import PyQuery
from pyquery.pyquery import fromstring
from fake_useragent import UserAgent
from lxml import etree
@@ -64,6 +65,8 @@ class BaseParser:
self.default_encoding = default_encoding
self._encoding = None
self._html = html.encode(DEFAULT_ENCODING) if isinstance(html, str) else html
self._lxml = None
self._pq = None
@property
def raw_html(self) -> _RawHTML:
@@ -81,7 +84,7 @@ class BaseParser:
(`learn more <http://www.diveintopython3.net/strings.html>`_).
"""
if self._html:
return self._html.decode(self.encoding)
return self.raw_html.decode(self.encoding)
else:
return etree.tostring(self.element, encoding='unicode').strip()
@@ -114,14 +117,20 @@ class BaseParser:
"""`PyQuery <https://pythonhosted.org/pyquery/>`_ representation
of the :class:`Element <Element>` or :class:`HTML <HTML>`.
"""
return PyQuery(self.element)
if self._pq is None:
self._pq = PyQuery(self.html)
return self._pq
@property
def lxml(self) -> HtmlElement:
"""`lxml <http://lxml.de>`_ representation of the
:class:`Element <Element>` or :class:`HTML <HTML>`.
"""
return soup_parse(self.html, features='html.parser')
if self._lxml is None:
self._lxml = soup_parse(self.html, features='html.parser')
return self._lxml
@property
def text(self) -> _Text:
@@ -291,7 +300,7 @@ class Element(BaseParser):
"""Returns a dictionary of the attributes of the :class:`Element <Element>`
(`learn more <https://www.w3schools.com/tags/ref_attributes.asp>`_).
"""
attrs = {k: self.pq.attr[k].strip() for k in self.element.keys()}
attrs = {k: v for k, v in self.element.items()}
# Split class up, as there are ussually many of them:
if 'class' in attrs:
tests/test_requests_html.py
+1 -1
View File
@@ -151,4 +151,4 @@ def test_bare_js_eval():
if __name__ == '__main__':
test_xpath()
test_anchor_links()