def test_parse_dom():
tag_list = [
dhtmlparser.HTMLElement("<h1>"),
dhtmlparser.HTMLElement("<xx>"),
dhtmlparser.HTMLElement("<xx>"),
dhtmlparser.HTMLElement("</h1>"),
]
dom = dhtmlparser._parseDOM(tag_list)
assert len(dom) == 2
assert len(first(dom).childs) == 2
assert first(dom).childs[0].getTagName() == "xx"
assert first(dom).childs[1].getTagName() == "xx"
assert first(dom).childs[0].isNonPairTag()
assert first(dom).childs[1].isNonPairTag()
assert not dom[0].isNonPairTag()
assert not dom[1].isNonPairTag()
assert dom[0].isOpeningTag()
assert dom[1].isEndTag()
assert dom[0].endtag == dom[1]
assert dom[1].openertag == dom[0]
assert dom[1].isEndTagTo(dom[0])
def test_parse_dom():
tag_list = [
dhtmlparser.HTMLElement("<h1>"),
dhtmlparser.HTMLElement("<xx>"),
dhtmlparser.HTMLElement("<xx>"),
dhtmlparser.HTMLElement("</h1>"),
]
dom = dhtmlparser._parseDOM(tag_list)
assert len(dom) == 2
assert len(first(dom).childs) == 2
assert first(dom).childs[0].getTagName() == "xx"
assert first(dom).childs[1].getTagName() == "xx"
assert first(dom).childs[0].isNonPairTag()
assert first(dom).childs[1].isNonPairTag()
assert not dom[0].isNonPairTag()
assert not dom[1].isNonPairTag()
assert dom[0].isOpeningTag()
assert dom[1].isEndTag()
assert dom[0].endtag == dom[1]
assert dom[1].openertag == dom[0]
assert dom[1].isEndTagTo(dom[0])
def _find_link_element(item):
link_el = item.find("link")
if not link_el:
return None
return first(link_el)
def test_wfind_complicated():
dom = dhtmlparser.parseString(
"""
<root>
<some>
<something>
<xe id="wanted xe" />
</something>
<something>
asd
</something>
<xe id="another xe" />
</some>
<some>
else
<xe id="yet another xe" />
</some>
</root>
"""
)
xe = dom.wfind("root").wfind("some").wfind("something").find("xe")
assert len(xe) == 1
assert first(xe).params["id"] == "wanted xe"
unicorn = dom.wfind("root").wfind("pink").wfind("unicorn")
assert not unicorn.childs
def test_match_parameters():
dom = dhtmlparser.parseString(
"""
<root>
<div id="1">
<div id="5">
<xe id="wanted xe" />
</div>
<div id="10">
<xe id="another wanted xe" />
</div>
<xe id="another xe" />
</div>
<div id="2">
<div id="20">
<xe id="last wanted xe" />
</div>
</div>
</root>
"""
)
xe = dom.match(
"root",
{"tag_name": "div", "params": {"id": "1"}},
["div", {"id": "5"}],
"xe"
)
assert len(xe) == 1
assert first(xe).params["id"] == "wanted xe"
def _pick_item_property(item, item_property):
prop = item.find(item_property)
if not prop:
return None
return first(prop).getContent()
def test_wfind_complicated():
dom = dhtmlparser.parseString("""
<root>
<some>
<something>
<xe id="wanted xe" />
</something>
<something>
asd
</something>
<xe id="another xe" />
</some>
<some>
else
<xe id="yet another xe" />
</some>
</root>
""")
xe = dom.wfind("root").wfind("some").wfind("something").find("xe")
assert len(xe) == 1
assert first(xe).params["id"] == "wanted xe"
unicorn = dom.wfind("root").wfind("pink").wfind("unicorn")
assert not unicorn.childs
def test_match_parameters():
dom = dhtmlparser.parseString("""
<root>
<div id="1">
<div id="5">
<xe id="wanted xe" />
</div>
<div id="10">
<xe id="another wanted xe" />
</div>
<xe id="another xe" />
</div>
<div id="2">
<div id="20">
<xe id="last wanted xe" />
</div>
</div>
</root>
""")
xe = dom.match("root", {
"tag_name": "div",
"params": {
"id": "1"
}
}, ["div", {
"id": "5"
}], "xe")
assert len(xe) == 1
assert first(xe).params["id"] == "wanted xe"
def _find_comments_link(item):
comments_link = item.find("comments")
if not comments_link:
return None
return first(comments_link).getContent()
def test_params():
dom = dhtmlparser.parseString("<xe id=1 />")
xe = first(dom.find("xe"))
assert xe.params["id"] == "1"
xe.params = {}
assert str(xe) == "<xe />"
def test_params():
dom = dhtmlparser.parseString("<xe id=1 />")
xe = first(dom.find("xe"))
assert xe.params["id"] == "1"
xe.params = {}
assert str(xe) == "<xe />"
def test_containsParamSubset():
dom = dhtmlparser.parseString("<div id=x class=xex></div>")
div = first(dom.find("div"))
assert div.containsParamSubset({"id": "x"})
assert div.containsParamSubset({"class": "xex"})
assert div.containsParamSubset({"id": "x", "class": "xex"})
assert not div.containsParamSubset({"asd": "bsd", "id": "x", "class": "xex"})
def test_isNonPairTag():
assert not div.isNonPairTag()
text = first(div.childs)
assert text.getTagName().strip() == "Second."
assert not text.isTag()
assert not text.isNonPairTag()
assert br.isNonPairTag()
def test_replaceWith():
nonpair = first(dom.find("nonpair"))
assert nonpair
nonpair.replaceWith(dhtmlparser.HTMLElement("<another />"))
assert dom.find("another")
assert dom.getContent() == "<div><another /></div>"
def test_find_params():
dom = dhtmlparser.parseString("""
<div id=first>
First div.
<div id=first.subdiv>
Subdiv in first div.
</div>
</div>
<div id=second>
Second.
</div>
""")
div_tags = dom.find("", {"id": "first"})
assert div_tags
assert len(div_tags) == 1
assert first(div_tags).params.get("id") == "first"
assert first(div_tags).getContent().strip().startswith("First div.")
def test_replaceWith():
nonpair = first(dom.find("nonpair"))
assert nonpair
nonpair.replaceWith(
dhtmlparser.HTMLElement("<another />")
)
assert dom.find("another")
assert dom.getContent() == "<div><another /></div>"
def test_recovery_after_is_smaller_than_sign():
inp = """<code>5 < 10.</code>
<div class="rating">here is the rating</div>
"""
dom = dhtmlparser.parseString(inp)
code = dom.find("code")
assert code
assert first(code).getContent() == "5 < 10."
assert dom.find("div", {"class": "rating"})
def test_recovery_after_is_smaller_than_sign():
inp = """<code>5 < 10.</code>
<div class="rating">here is the rating</div>
"""
dom = dhtmlparser.parseString(inp)
code = dom.find("code")
assert code
assert first(code).getContent() == "5 < 10."
assert dom.find("div", {"class": "rating"})
def test_find():
dom = dhtmlparser.parseString("""
"<div ID='xa' a='b'>obsah xa divu</div> <!-- ID, not id :) -->
<div id='xex' a='b'>obsah xex divu</div>
""")
div_xe = dom.find("div", {"id": "xa"}) # notice the small `id`
div_xex = dom.find("div", {"id": "xex"})
div_xerexes = dom.find("div", {"id": "xerexex"})
assert div_xe
assert div_xex
assert not div_xerexes
div_xe = first(div_xe)
div_xex = first(div_xex)
assert div_xe.toString() == '<div ID="xa" a="b">obsah xa divu</div>'
assert div_xex.toString() == '<div id="xex" a="b">obsah xex divu</div>'
assert div_xe.getTagName() == "div"
assert div_xex.getTagName() == "div"
def test_find_params():
dom = dhtmlparser.parseString(
"""
<div id=first>
First div.
<div id=first.subdiv>
Subdiv in first div.
</div>
</div>
<div id=second>
Second.
</div>
"""
)
div_tags = dom.find("", {"id": "first"})
assert div_tags
assert len(div_tags) == 1
assert first(div_tags).params.get("id") == "first"
assert first(div_tags).getContent().strip().startswith("First div.")
def test_find():
dom = dhtmlparser.parseString(
"""
"<div ID='xa' a='b'>obsah xa divu</div> <!-- ID, not id :) -->
<div id='xex' a='b'>obsah xex divu</div>
"""
)
div_xe = dom.find("div", {"id": "xa"}) # notice the small `id`
div_xex = dom.find("div", {"id": "xex"})
div_xerexes = dom.find("div", {"id": "xerexex"})
assert div_xe
assert div_xex
assert not div_xerexes
div_xe = first(div_xe)
div_xex = first(div_xex)
assert div_xe.toString() == '<div ID="xa" a="b">obsah xa divu</div>'
assert div_xex.toString() == '<div id="xex" a="b">obsah xex divu</div>'
assert div_xe.getTagName() == "div"
assert div_xex.getTagName() == "div"
def test_closeElements():
tag = dhtmlparser.HTMLElement("<div>")
tag.endtag = dhtmlparser.HTMLElement("</div>")
tag.childs = [dhtmlparser.HTMLElement("<xe>")]
xe = tag.find("xe")
assert xe
assert not xe[0].endtag
tag.chids = _closeElements(tag.childs, dhtmlparser.HTMLElement)
xe = tag.find("xe")
assert xe
assert first(xe).endtag
def test_closeElements():
tag = dhtmlparser.HTMLElement("<div>")
tag.endtag = dhtmlparser.HTMLElement("</div>")
tag.childs = [
dhtmlparser.HTMLElement("<xe>")
]
xe = tag.find("xe")
assert xe
assert not xe[0].endtag
tag.chids = _closeElements(tag.childs, dhtmlparser.HTMLElement)
xe = tag.find("xe")
assert xe
assert first(xe).endtag
def test_multiline_attribute():
inp = """<sometag />
<ubertag attribute="long attribute
continues here">
<valid>notice that quote is not properly started</valid>
</ubertag>
<something_parsable />
"""
dom = dhtmlparser.parseString(inp)
assert dom.find("sometag")
assert dom.find("valid")
assert dom.find("ubertag")
assert first(dom.find("ubertag")).params["attribute"] == """long attribute
continues here"""
assert dom.find("something_parsable")
def test_wfind():
dom = dhtmlparser.parseString("""
<div id=first>
First div.
<div id=first.subdiv>
Subdiv in first div.
</div>
</div>
<div id=second>
Second.
</div>
""")
div = dom.wfind("div").wfind("div")
assert div.childs
assert first(div.childs).params["id"] == "first.subdiv"
def test_multiline_attribute():
inp = """<sometag />
<ubertag attribute="long attribute
continues here">
<valid>notice that quote is not properly started</valid>
</ubertag>
<something_parsable />
"""
dom = dhtmlparser.parseString(inp)
assert dom.find("sometag")
assert dom.find("valid")
assert dom.find("ubertag")
assert first(dom.find("ubertag")).params["attribute"] == """long attribute
continues here"""
assert dom.find("something_parsable")
def test_wfind():
dom = dhtmlparser.parseString(
"""
<div id=first>
First div.
<div id=first.subdiv>
Subdiv in first div.
</div>
</div>
<div id=second>
Second.
</div>
"""
)
div = dom.wfind("div").wfind("div")
assert div.childs
assert first(div.childs).params["id"] == "first.subdiv"
def test_isOpeningTag():
assert div.isOpeningTag()
assert not first(div.childs).isOpeningTag()
assert not br.isOpeningTag()
def test_getTagName():
assert div.getTagName() == 'div'
assert first(div.childs).getTagName() == '\n Second.\n '
assert br.getTagName() == "br"
def test_isTag():
assert div.isTag()
assert not first(div.childs).isTag()
def _construct_new_link_el(url):
dom = dhtmlparser.parseString("<link>%s</link>" % url)
return first(dom.find("link"))
def test_isEndTag():
assert not div.isEndTag()
assert not first(div.childs).isEndTag()
assert div.endtag.isEndTag()
def test_isComment():
assert not div.isComment()
assert not first(div.childs).isComment()
assert div.childs[-2].isComment()
def test_getContent():
match = '\n Second.\n <br />\n <!-- comment -->\n '
assert div.getContent() == match
assert first(div.childs).getContent() == '\n Second.\n '
assert br.getContent() == ""
def test_tagToString():
assert div.tagToString() == '<div id="second">'
assert first(div.childs).tagToString() == '\n Second.\n '
assert br.tagToString() == "<br />"
# Variables ===================================================================
DOM = dhtmlparser.parseString("""
<div id=first>
First div.
<div id=first.subdiv>
Subdiv in first div.
</div>
</div>
<div id=second>
Second.
<br />
<!-- comment -->
</div>
""")
div = DOM.find("div")[-1]
br = first(div.find("br"))
# Functions & objects =========================================================
def test_isTag():
assert div.isTag()
assert not first(div.childs).isTag()
def test_isEndTag():
assert not div.isEndTag()
assert not first(div.childs).isEndTag()
assert div.endtag.isEndTag()
def test_toString():
assert div.toString().startswith(div.tagToString())
assert first(div.childs).toString() == '\n Second.\n '
assert br.toString() == "<br />"