# ruff: noqa: RUF001
def test_text_from_html_success_english():
"""
Given
- html string:
This is heading 1
When
- extracting text from the html
Then
- ensure we return "This is heading 1"
"""
import TextFromHTML
html = """
This is heading 1
"""
body = TextFromHTML.get_body(html, html_tag="body")
res = TextFromHTML.get_plain_text(body, replace_line_breaks=False, trim_result=False)
assert res == "\nThis is heading 1\n"
def test_text_from_html_success_hebrew():
"""
Given
- html string:
משפט בעברית לבדיקה
When
- extracting text from the html
Then
- ensure we return "משפט בעברית לבדיקה"
"""
import TextFromHTML
html = """
משפט בעברית לבדיקה
"""
body = TextFromHTML.get_body(html, html_tag="body")
res = TextFromHTML.get_plain_text(body, replace_line_breaks=False, trim_result=False)
assert res == "\nמשפט בעברית לבדיקה\n"
def test_text_from_html_success_spanish():
"""
Given
- html string:
Frase en español para revisión
When
- extracting text from the html
Then
- ensure we return "Frase en español para revisión"
"""
import TextFromHTML
html = """
Frase en español para revisión
"""
body = TextFromHTML.get_body(html, html_tag="body")
res = TextFromHTML.get_plain_text(body, replace_line_breaks=False, trim_result=False)
assert res == "\nFrase en español para revisión\n"
def test_extract_text_from_complex_html():
"""
Given
- html string:
HTML Links
HTML links are defined with the a tag:
This is a link
When
- extracting text from the html
Then
- ensure we return "This is heading 1"
"""
import TextFromHTML
html = """
HTML Links
HTML links are defined with the a tag:
This is a link
"""
body = TextFromHTML.get_body(html, html_tag="body")
res = TextFromHTML.get_plain_text(body, replace_line_breaks=False, trim_result=False)
assert res == "\n\nHTML Links\nHTML links are defined with the a tag:\n\nThis is a link\n\n"
def test_extract_text_from_html_with_breaks():
"""
Given
- html string:
HTML Breaks
HTML can contain break tags
Which should lead to a proper linebreak
When
- extracting text from the html
Then
- ensure we return "\nHTML Breaks\nHTML can contain break tags\n\n\nWhich should lead to a proper linebreak"
"""
import TextFromHTML
html = """
HTML Breaks
HTML can contain break tags
Which should lead to a proper linebreak
"""
body = TextFromHTML.get_body(html, html_tag="body")
res = TextFromHTML.get_plain_text(body, replace_line_breaks=True, trim_result=False)
assert res == "\nHTML Breaks\nHTML can contain break tags\n\n\nWhich should lead to a proper linebreak\n"
def test_extract_text_from_html_with_breaks_trimed():
"""
Given
- html string:
HTML Breaks
HTML can contain break tags
Which should lead to a proper linebreak
When
- extracting text from the html with replace_line_breaks and trim_result enabled
Then
- ensure we return "HTML Breaks\nHTML can contain break tags\n\nWhich should lead to a proper linebreak"
"""
import TextFromHTML
html = """
HTML Breaks
HTML can contain break tags
Which should lead to a proper linebreak
"""
body = TextFromHTML.get_body(html, html_tag="body")
res = TextFromHTML.get_plain_text(body, replace_line_breaks=True, trim_result=True)
assert res == "HTML Breaks\nHTML can contain break tags\n\nWhich should lead to a proper linebreak"
def test_extract_text_from_specific_tag():
"""
Given
- html string:
HTML links are defined with the a tag:
When
- extracting text from the html
Then
- ensure we return "HTML links are defined with the a tag:"
"""
import TextFromHTML
html = """HTML links are defined with the a tag:
"""
body = TextFromHTML.get_body(html, html_tag="p")
res = TextFromHTML.get_plain_text(body, replace_line_breaks=False, trim_result=False)
assert res == "HTML links are defined with the a tag:"
def test_extract_with_fallback():
"""
Given
- html string:
Some HTML does not have a body Tag
When
- extracting text from the html with fallback enabled
Then
- ensure we return "Some HTML does not have a body Tag"
"""
import TextFromHTML
html = """Some HTML does not have a body Tag
"""
body = TextFromHTML.get_body(html, html_tag="body", allow_fallback=True)
res = TextFromHTML.get_plain_text(body, replace_line_breaks=False, trim_result=False)
assert res == "Some HTML does not have a body Tag"
def test_extract_without_fallback():
"""
Given
- html string:
Some HTML does not have a body Tag
When
- extracting text from the html
Then
- ensure we return ""
"""
import TextFromHTML
html = """Some HTML does not have a body Tag
"""
body = TextFromHTML.get_body(html, html_tag="body", allow_fallback=False)
res = TextFromHTML.get_plain_text(body, replace_line_breaks=False, trim_result=False)
assert res == ""
def test_get_body():
"""
Given
- html string:
This is heading 1
When
- extracting body from html
Then
- ensure we return "\nThis is heading 1
\n"
"""
import TextFromHTML
html = """
This is heading 1
"""
body = TextFromHTML.get_body(html, html_tag="body", allow_fallback=False)
assert body == "\nThis is heading 1
\n"
def test_get_body_without_fallback():
"""
Given
- html string:
Some HTML does not have a body Tag
When
- extracting body from html
Then
- ensure we return ""
"""
import TextFromHTML
html = """Some HTML does not have a body Tag
"""
body = TextFromHTML.get_body(html, html_tag="body", allow_fallback=False)
assert body == ""
def test_get_body_with_fallback():
"""
Given
- html string:
Some HTML does not have a body Tag
When
- extracting body from html
Then
- ensure we return ""
"""
import TextFromHTML
html = """Some HTML does not have a body Tag
"""
body = TextFromHTML.get_body(html, html_tag="body", allow_fallback=True)
assert body == "Some HTML does not have a body Tag
"