59 lines
1.7 KiB
Python
59 lines
1.7 KiB
Python
"""Tests for extract.* commands (require an http/https active tab)."""
|
|
|
|
|
|
def test_extract_links(browser, http_tab):
|
|
browser("tabs.active", {"tabId": http_tab["id"]})
|
|
links = browser("extract.links")
|
|
assert isinstance(links, list)
|
|
hrefs = []
|
|
for lnk in links:
|
|
assert "href" in lnk
|
|
assert "text" in lnk
|
|
hrefs.append(lnk["href"])
|
|
assert len(hrefs) == len(set(hrefs))
|
|
|
|
|
|
def test_extract_images(browser, http_tab):
|
|
browser("tabs.active", {"tabId": http_tab["id"]})
|
|
images = browser("extract.images")
|
|
assert isinstance(images, list)
|
|
sources = []
|
|
for img in images:
|
|
assert "src" in img
|
|
assert img["src"] != ""
|
|
sources.append(img["src"])
|
|
assert len(sources) == len(set(sources))
|
|
|
|
|
|
def test_extract_text(browser, http_tab):
|
|
browser("tabs.active", {"tabId": http_tab["id"]})
|
|
text = browser("extract.text")
|
|
assert isinstance(text, str)
|
|
assert len(text) > 0
|
|
|
|
|
|
def test_extract_html(browser, http_tab):
|
|
browser("tabs.active", {"tabId": http_tab["id"]})
|
|
html = browser("extract.html")
|
|
assert isinstance(html, str)
|
|
assert "<" in html
|
|
|
|
|
|
def test_extract_markdown(browser, http_tab):
|
|
browser("tabs.active", {"tabId": http_tab["id"]})
|
|
markdown = browser("extract.markdown")
|
|
assert isinstance(markdown, str)
|
|
assert len(markdown.strip()) > 0
|
|
|
|
|
|
def test_extract_markdown_missing_selector_errors(browser, http_tab):
|
|
browser("tabs.active", {"tabId": http_tab["id"]})
|
|
assert browser("dom.exists", {"selector": ".browser-cli-definitely-missing"}) is False
|
|
|
|
try:
|
|
browser("extract.markdown", {"selector": ".browser-cli-definitely-missing"})
|
|
except RuntimeError as exc:
|
|
assert "No element" in str(exc)
|
|
|
|
|