Created
May 13, 2022 08:09
-
-
Save eleco/294774e8dc075904ff5b61a2b08f4162 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import asyncio | |
from pyppeteer import launch | |
async def get_article_titles(keywords): | |
# launch browser in headless mode | |
browser = await launch({"headless": False, "args": ["--start-maximized"]}) | |
# create a new page | |
page = await browser.newPage() | |
# set page viewport to the largest size | |
await page.setViewport({"width": 1600, "height": 900}) | |
# navigate to the page | |
await page.goto("https://www.google.fr/search?q=strategy journey") | |
# wait for search results to load | |
await page.waitFor(1000) | |
pages = await browser.pages(); | |
print(pages) | |
popup = pages[1] | |
x = await popup.querySelectorAll("button") | |
for xx in x: | |
title = await xx.getProperty("textContent") | |
tilej = await title.jsonValue() | |
if tilej == 'I agree': | |
await xx.click() | |
await page.waitFor(100) | |
# btn = await popup.xpath('//button[contains(text(),"e")]') | |
# wait page.click('//button[contains(text(),"I agree")]') | |
url = await page.evaluate("() => window.location.href") | |
print(url) | |
# extract the article titles | |
#topics = await page.querySelectorAll("a>div>h3") | |
results = await page.Jx("//div[@class = 'g']//a[h3]"); | |
#topics = await page.evaluate('(results) => results.href' ,results) | |
for topic in results: | |
title = await topic.getProperty("textContent") | |
print(await title.jsonValue()) | |
link = await topic.getProperty("href") | |
prize_href = await page.evaluate('(g) => g.href', topic) | |
# print the article titles | |
print(prize_href) | |
print(await link.jsonValue()) | |
print("Starting...") | |
asyncio.get_event_loop().run_until_complete( | |
get_article_titles(["python", "opensource", "opencv"]) | |
) | |
print("Finished extracting articles titles") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment