async def read_page(browserurl, targeturl):
"""
read a page and get the title
originally https://github.com/HyperionGray/trio-chrome-devtools-protocol/blob/master/examples/get_title.py
"""
logger.info("Connecting to browser: %s", browserurl)
async with open_cdp(browserurl) as conn:
logger.info("Listing targets")
targets = await conn.execute(target.get_targets())
target_id = targets[0].target_id
logger.info("Attaching to target id=%s", target_id)
session = await conn.open_session(target_id)
logger.info("Navigating to %s", targeturl)
await session.execute(page.enable())
async with session.wait_for(page.LoadEventFired):
await session.execute(page.navigate(targeturl))
_, item = await session.execute(page.print_to_pdf())
print(f"pdf is: {type(item)}")
logger.info("Extracting page title")
root_node = await session.execute(dom.get_document())
title_node_id = await session.execute(
dom.query_selector(root_node.node_id, "title")
)
html = await session.execute(dom.get_outer_html(title_node_id))
async def main():
logger.info('Connecting to browser: %s', sys.argv[1])
async with open_cdp_connection(sys.argv[1]) as conn:
logger.info('Listing targets')
targets = await conn.execute(target.get_targets())
for t in targets:
if (t.type == 'page' and not t.url.startswith('devtools://')
and not t.attached):
target_id = t.target_id
break
logger.info('Attaching to target id=%s', target_id)
session = await conn.open_session(target_id)
logger.info('Navigating to %s', sys.argv[2])
await session.execute(page.enable())
async with session.wait_for(page.LoadEventFired):
await session.execute(page.navigate(sys.argv[2]))
logger.info('Extracting page title')
root_node = await session.execute(dom.get_document())
title_node_id = await session.execute(
dom.query_selector(root_node.node_id, 'title'))
html = await session.execute(dom.get_outer_html(title_node_id))
print(html)
async def save_pdf(browserurl, targeturl, pdfpath, sleeptime):
"""
make a pdf from a webpage
originally https://github.com/HyperionGray/trio-chrome-devtools-protocol/blob/master/examples/screenshot.py
Parameters
browserurl: str
ws address for chrome developer protocol commands
targeturl: str
url of page to print to pdf
pngfile: str
filename for png file
"""
logger.info("Connecting to browser: %s", browserurl)
async with open_cdp(browserurl) as conn:
logger.info("Listing targets")
targets = await conn.execute(target.get_targets())
target_id = targets[0].target_id
logger.info("Attaching to target id=%s", target_id)
async with conn.open_session(target_id) as session:
logger.info("Setting device emulation")
await session.execute(
emulation.set_device_metrics_override(
width=1200, height=2000, device_scale_factor=1, mobile=False
)
)
logger.info("Enabling page events")
await session.execute(page.enable())
logger.info("Navigating to %s", targeturl)
async with session.wait_for(page.LoadEventFired):
await session.execute(page.navigate(url=targeturl))
time.sleep(sleeptime)
root_node = await session.execute(dom.get_document())
title_node_id = await session.execute(
dom.query_selector(root_node.node_id, "body")
)
body_html = await session.execute(dom.get_outer_html(title_node_id))
logger.debug(body_html)
logger.info("Saving a pdf")
# TODO: make sure that javascript finishes rendering
# await session.execute(page.capture_screenshot(format="png"))
pdf_data, _ = await session.execute(page.print_to_pdf())
pdf_file = await trio.open_file(pdfpath, "wb")
async with pdf_file:
await pdf_file.write(b64decode(pdf_data))
logger.info(f"wrote {pdfpath}")
async def convert_page(session, path, reduction_code):
urlpath = 'file://' + os.path.abspath(path)
logger.info('Navigating to %s', urlpath)
async with session.wait_for(page.LoadEventFired):
await session.execute(page.navigate(url=urlpath))
(_, exc) = await session.execute(runtime.evaluate(reduction_code))
root_id = (await session.execute(dom.get_document())).node_id
main_id = await session.execute(dom.query_selector(root_id, '#main'))
return await session.execute(dom.get_outer_html(main_id))
async def merge_pages_in(ethox_doc, ws_addr, reduction_code):
async with open_cdp_connection(ws_addr) as conn:
logger.info('Listing targets')
targets = await conn.execute(target.get_targets())
target_id = targets[0].target_id
logger.info('Attaching to target id=%s', target_id)
session = await conn.open_session(target_id)
logger.info('Setting device emulation')
await session.execute(
emulation.set_device_metrics_override(width=800,
height=600,
device_scale_factor=1,
mobile=False))
logger.info('Enabling page events')
await session.execute(page.enable())
logger.info('Starting to crawl documentation')
contents = {}
for doc_page in glob.iglob(os.path.join(ethox_doc, '**', '*.html'),
recursive=True):
(target_item,
main_contents) = await convert_page(session, doc_page,
reduction_code)
contents[target_item] = main_contents
await convert_page(session, os.path.join(ethox_doc, 'index.html'),
reduction_code)
root_id = (await session.execute(dom.get_document())).node_id
body_id = await session.execute(dom.query_selector(root_id, 'body'))
footer_id = await session.execute(dom.query_selector(
root_id, 'footer'))
main_id = await session.execute(dom.query_selector(root_id, '#main'))
for (_, contents) in contents.items():
cloned_id = await session.execute(
dom.copy_to(main_id, body_id, footer_id))
await session.execute(dom.set_outer_html(cloned_id, contents))
await print_page(session, 'cargo_doc.pdf')
async def main():
logger.info('Connecting to browser: %s', sys.argv[1])
async with open_cdp_connection(sys.argv[1]) as conn:
logger.info('Listing targets')
targets = await conn.execute(target.get_targets())
target_id = targets[0].target_id
logger.info('Attaching to target id=%s', target_id)
session = await conn.open_session(target_id)
logger.info('Navigating to %s', sys.argv[2])
await session.execute(page.enable())
await session.execute(page.navigate(sys.argv[2]))
event = await session.wait_for(page.LoadEventFired)
logger.info('Extracting page title')
root_node = await session.execute(dom.get_document())
title_node_id = await session.execute(
dom.query_selector(root_node.node_id, 'title'))
html = await session.execute(dom.get_outer_html(title_node_id))
print(html)
