def test_nested_quotes(self):
expected_output = self.load_md("nested_quote2")
quotebox = md.MarkdownQuotebox()
quotebox.add(md.MarkdownParagraph("Paragraph 1"))
nested_quotebox = md.MarkdownQuotebox()
nested_quotebox.add(md.MarkdownParagraph("Paragraph 2 (nested)"))
quotebox.add(nested_quotebox)
quotebox.add(md.MarkdownParagraph("Paragraph 3"))
self.assertEqual(expected_output, str(quotebox))
expected_output = self.load_md("nested_quote3")
level_0 = md.MarkdownDocument()
level_1 = md.MarkdownQuotebox()
level_2 = md.MarkdownQuotebox()
level_3 = md.MarkdownQuotebox()
level_0.add(md.MarkdownParagraph("Outside quotes!"))
level_1.add(md.MarkdownParagraph("First level"))
level_2.add(md.MarkdownParagraph("Second level"))
level_3.add(md.MarkdownParagraph("Third level"))
level_0.add(level_1)
level_1.add(level_2)
level_2.add(level_3)
level_1.add(md.MarkdownParagraph("Back on the first level"))
level_0.add(
md.MarkdownLink("Link at the end of the document",
"https://nowhere.com"))
self.assertEqual(expected_output, str(level_0))
def process_img(img):
# use alt text instead if available
if img.has_attr("alt") and img["alt"]:
text = img["alt"]
else:
text = "Image Link"
link = img["src"]
return md.MarkdownLink(text, link)
def process_iframe(iframe):
# these are used for youtube videos. I'll make the text something else
# if the src doesn't point to youtube
src = iframe["src"]
if "youtube" in src:
text = "Youtube Video"
else:
text = "Embedded content"
# do some filtering for different kinds of youtube links
id_indicators = ["youtube.com/embed/", "youtube.com/watch?v="]
video_id = ""
for indic in id_indicators:
if src.find(indic) != -1:
video_id = src[src.find(indic) + len(indic):]
if video_id:
link = "https://www.youtube.com/watch?v=" + video_id
else:
link = src
return str(md.MarkdownLink(text, link)) + ITEM_SEPARATOR
def test_link_with_parentheses(self):
expected_output = self.load_md("link_escapes")
link = md.MarkdownLink(
"escaped parentheses",
"https://example.com/long_item_name_with(parentheses)")
self.assertEqual(expected_output, str(link))
def test_link(self):
expected_output = self.load_md("link")
link = md.MarkdownLink("link text", "example.com/link")
self.assertEqual(expected_output, str(link))
def convert_tag(tag):
content_inside_this_tag = process_tag(tag)
# tags that don't auto insert newline are processed first
if tag.name == "a" and tag.has_attr("href"):
return md.MarkdownLink(content_inside_this_tag, tag["href"])
elif tag.name == "a":
return content_inside_this_tag
# these can be handled the same as far as I can tell
elif tag.name == "code" or tag.name == "pre":
return process_code(tag)
elif tag.name == "strong":
return process_strong(content_inside_this_tag)
elif tag.name == "span":
return content_inside_this_tag
elif tag.name == "em":
return process_italics(content_inside_this_tag)
elif tag.name == "img":
return process_img(tag)
elif tag.name == "table":
return process_table(tag)
elif tag.name == "ul":
temp = ITEM_SEPARATOR + content_inside_this_tag
if len(temp) > 2 and temp[-2:] != "\n\n":
temp += "\n"
return temp
elif tag.name == "br":
return "\n\n"
elif is_excluded_tag(tag):
return ""
# tags below here insert a newline if not already inserted by previous call to convert_tag
if tag.name == "p":
output = md.MarkdownParagraph(content_inside_this_tag)
elif tag.name == "div":
output = md.MarkdownParagraph(content_inside_this_tag)
elif tag.name == "h2":
output = md.MarkdownHeader(content_inside_this_tag, 2)
elif tag.name == "h3":
output = md.MarkdownHeader(content_inside_this_tag, 3)
elif tag.name == "li":
output = md.MarkdownListItem(content_inside_this_tag)
elif tag.name == "blockquote":
output = process_quote_box(tag, content_inside_this_tag)
elif tag.name == "iframe":
output = process_iframe(tag)
elif tag.name == "video":
if tag.has_attr("src"):
output = str(md.MarkdownLink("Embedded Video",
tag["src"])) + ITEM_SEPARATOR
elif tag.children is not None and tag.find("source").has_attr("src"):
output = str(
md.MarkdownLink("Embedded Video",
tag.find("source")["src"])) + ITEM_SEPARATOR
else:
output = md.MarkdownParagraph(content_inside_this_tag)
else:
# default case should be fine for remaining tags
output = content_inside_this_tag
#if isinstance(output, md.MarkdownQuotebox) and len(output.items) == 3 and "Level 1 Cast when" in output.items[0]:
# print(output.items)
return output