Files
rrk-crawling/crawlingrrk.py

35 lines
1.1 KiB
Python

from time import sleep
from playwright.sync_api import sync_playwright
pw = sync_playwright().start()
firefox = pw.firefox.launch(headless=False)
context = firefox.new_context(ignore_https_errors=True)
page = context.new_page()
page.goto(
"https://rrk.ir/ords/r/rrs/rrs-front/%D8%AF%D8%A7%D8%AF%D9%87-%D8%A8%D8%A7%D8%B2"
)
page.locator("#P199_SABTNODATE_AZ").fill("1404/09/20")
page.locator("#P199_NEWSPAPERDATE_AZ").fill("1404/10/01")
page.locator("#B912476867105247978").click()
print("reached")
sleep(4)
table = page.locator(".a-GV-table").nth(1)
print("table is found")
rows = table.locator("tbody tr")
print("rows found")
rows.first.wait_for()
for i in range(rows.count()):
print(rows.nth(i).inner_html())
link = "https://rrk.ir" + rows.nth(i).locator("td a").last.get_attribute("href")
newPage = page.context.new_page()
newPage.goto(link)
detailedData = newPage.locator(
"#R41756901674822518 > div.t-Region-bodyWrap > div.t-Region-body > div.container "
)
with open("htmldocs/" + str(i) + ".html", "w+", encoding="utf-8") as file:
file.write(detailedData.inner_html())
newPage.close()
sleep(5)