Scrapy と Playwright を使用した無限スクロールによるページのクロール

uv venv 
source .venv/bin/activate

uv pip install scrapy-playwright

playwright install chromium

# settings.py
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"

DOWNLOAD_HANDLERS = {
    "http": "scrapy_playwright.handler.ScrapyPlaywrightDownloadHandler",
    "https": "scrapy_playwright.handler.ScrapyPlaywrightDownloadHandler",
}

PLAYWRIGHT_LAUNCH_OPTIONS = {
    # optional for CORS issues
    "args": [
        "--disable-web-security",
        "--disable-features=IsolateOrigins,site-per-process",
    ],
    # optional for debugging
    "headless": False,
},

"PLAYWRIGHT_LAUNCH_OPTIONS": {
    "args": [
        "--disable-web-security",
        "--disable-features=IsolateOrigins,site-per-process",
    ],
    "headless": False,
}

# /<project>/spiders/infinite_scroll.py

import scrapy

from scrapy.spiders import CrawlSpider
from scrapy.selector import Selector


class InfinitePageSpider(CrawlSpider):
    """
    Spider to crawl an infinite scroll page
    """

    name = "infinite_scroll"

    allowed_domains = ["<allowed_domain>"]
    start_urls = ["<start_url>"]

    custom_settings = {
        "TWISTED_REACTOR": "twisted.internet.asyncioreactor.AsyncioSelectorReactor",
        "DOWNLOAD_HANDLERS": {
            "https": "scrapy_playwright.handler.ScrapyPlaywrightDownloadHandler",
            "http": "scrapy_playwright.handler.ScrapyPlaywrightDownloadHandler",
        },
        "PLAYWRIGHT_LAUNCH_OPTIONS": {
            "args": [
                "--disable-web-security",
                "--disable-features=IsolateOrigins,site-per-process",
            ],
            "headless": False,
        },
        "LOG_LEVEL": "INFO",
    }

    def start_requests(self):
        yield scrapy.Request(
            url=f"{self.start_urls[0]}",
            meta=dict(
                playwright=True,
                playwright_include_page=True,
            ),
            callback=self.parse,
        )


    async def parse(
        self,
        response,
    ):
        page = response.meta["playwright_page"]
        page.set_default_timeout(10000)

        await page.wait_for_timeout(5000)
            try:
                last_position = await page.evaluate("window.scrollY")

                while True:
                    # scroll by 700 while not at the bottom
                    await page.evaluate("window.scrollBy(0, 700)")
                    await page.wait_for_timeout(750) # wait for 750ms for the request to complete
                    current_position = await page.evaluate("window.scrollY")

                    if current_position == last_position:
                        print("Reached the bottom of the page.")
                        break

                    last_position = current_position

            except Exception as error:
                print(f"Error: {error}")
                pass

            print("Getting content")
            content = await page.content()

            print("Parsing content")
            selector = Selector(text=content)

            print("Extracting links")
            links = selector.xpath("//a[contains(@href, '/<link-pattern>/')]//@href").getall()

            print(f"Found {len(links)} links...")

            print("Yielding links")

            for link in links:
                yield {"link": link}

def start_requests(self):
    yield scrapy.Request(
        url=f"{self.start_urls[0]}",
        meta=dict(
            playwright=True,
            playwright_include_page=True,
        ),
        callback=self.parse,
    )

...

try:
    while True:
        button = page.locator('//button[contains(., "Load more")]')
        await button.wait_for()

        if not button:
            print("No 'Load more' button found.")
            break

        is_disabled = await button.is_disabled()
        if is_disabled:
            print("Button is disabled.")
            break

        await button.scroll_into_view_if_needed()
        await button.click()
        await page.wait_for_timeout(750)

except Exception as error:
    print(f"Error: {error}")
    pass

...