Created
June 10, 2024 14:58
-
-
Save valuex/3c8497584c0d78f6aee1e7144005583e to your computer and use it in GitHub Desktop.
1
This file contains hidden or 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
from playwright.sync_api import sync_playwright | |
from playwright.sync_api import Page, expect | |
import re | |
import time | |
# def get_exhibit_items() | |
def main(): | |
with sync_playwright() as p: | |
browser=p.chromium.launch(headless=False,timeout=0) | |
# page=browser.new_page() | |
context = browser.new_context() | |
page = context.new_page() | |
for ipage in range(11): | |
page_url='https://unifiedsearch.jcdbizmatch.jp/jpca2024/jp/jpca/product?page='+str(ipage)+'&items=3&order=1' | |
page.goto(page_url,timeout=60000) | |
page.wait_for_selector('text=製品',timeout=12000) | |
time.sleep(3) | |
item_divs=page.locator('div[class=\"col-inner\"]').all() | |
for each_item in item_divs: | |
try: | |
item_href=each_item.get_attribute('onclick') | |
item_name=each_item.locator('strong').inner_text() | |
# print(item_href) | |
# print(item_name) | |
except: | |
pass | |
grandparent = each_item.locator('xpath=../..') | |
label_divs=grandparent.locator('div').all() | |
try: | |
img_obj=label_divs[2] | |
post_img=img_obj.locator('img').all()[1] | |
post_img_url=post_img.get_attribute('src') | |
except: | |
post_img_url="" | |
exhibit_div=label_divs[3] | |
exhibit_name=exhibit_div.inner_text() | |
exhibit_item=item_href+'\t'+item_name+'\t'+exhibit_name+'\t'+post_img_url | |
print(exhibit_item) | |
if __name__=="__main__": | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment