# puppeteer支支持字典傳參
browser = await launch({'headless':True})

# pyppeteer支持字典和關(guān)鍵字傳參
browser = await launch({'headless':True})
browser = await launch(headless=True)

# puppeteer使用$符
page.$()/page.%%()/page.$x()

# pyppeteer使用python風(fēng)格的函數(shù)名
page.querySelector()/page.querySelectorAll()/page.xpath()

# 簡(jiǎn)寫(xiě)方式
page.J()/page.JJ()/page.Jx()

content = await page.evaluate('document.body.textContent',force_expr=True)

element = await page.querySelector('h1')
title = await page.evaluate('(element) => element.textContent',element)

pip install pyppeteer

pyppeteer-install

import asyncio
from pyppeteer import launch

async def main():
    url = 'https://www.toutiao.com/'
    # headless參數(shù)設(shè)置為Falase，則變成有頭模式
    browser = await launch(headless=False, ignoreDefaultArgs=['--enable-automation'])
    page = await browser.newPage()
    
    # 設(shè)置頁(yè)面視圖大小
    await page.setViewport(viewport={'width':1600,'herght':900})
    
    # 是否啟用JS，enabled設(shè)為False，則無(wú)渲染效果
    await page.setJavaScriptEnable(enabled=True)
    
    # 等待時(shí)間1000毫秒
    res = await page.goto(url，options={'timeout':1000})
    resp_headers = res.headers  # 響應(yīng)頭
    resp_status = res.status    # 響應(yīng)狀態(tài)
    
    # 等待
    await asyncio.sleep(2)
    await page.waitFor(1000)
    # 第二種方法 ，在while循環(huán)里強(qiáng)行查詢某元素進(jìn)行等待
    while not await page.querySelector('.t')
    
    # 滾動(dòng)到頁(yè)面底部
    await page.evaluate('window.scrollBy(0,document.body.scrollHeight)')
    
    await page.screenshot({'path':'test.png'})
    
    # 打印網(wǎng)頁(yè)cookies
    print(await page.cookies())
    
    # 獲取所有html內(nèi)容
    print(await page.content())
    
    
    dimensions = await page.evaluate(pageFunction='''() => {
    		return {
    			width:document.documentElement.clentWidth,    // 頁(yè)面寬度
    			height:document.documentElement.clentHeight,  // 頁(yè)面高度
    			deviceScaleFactor: window.devicePixelRatio,  // 像素比1.0000000149011612
    			}
    		}''',force_expr=False)   # force_expr=False  執(zhí)行的是函數(shù)
    print(dimensions)
    
    content = await page.evaluate(pageFunction='document.body.textContent',force_expr=True)    # 只獲得文本 執(zhí)行js腳本，force_expr=True  執(zhí)行的是表達(dá)式
    print(content)
    
    # 打印當(dāng)前頁(yè)面的標(biāo)題
    print(await page.title())
    
    
    # 抓取新聞內(nèi)容  可以使用xpath表達(dá)式
    '''
    pyppeteer 三種解析方式
    page.querySelector()
    page.querySelectorAll()
    page.xpath()
    簡(jiǎn)寫(xiě)方式為：
    page.J()
    page.JJ()
    page.Jx()
    '''
    element = await page.querySelector(".feed-infinite-wrapper > ul>li")
    print(element)
    
    
    element = await page.querySelectorAll(".title-box a")
    for item in element:
        print(await item.getProperty('textContent'))
        # 獲取文本內(nèi)容
        title_str = await (await item.getProperty('textContent')).jsonValue()
        
        title_link = await (await item.getProperty('textContent')).jsonValue()
        
        # 獲取屬性值
        # title = await (await item.getProperty('class')).jsonValue()
        print(title_str,title_link)
    await browser.close()


asyncio.get_event_loop().run_until_complete(main())

# 模擬輸入賬號(hào)密碼 參數(shù){'delay':reand_int()}  延遲輸入時(shí)間
await page.type('#kw',"百度",delay=100)
await page.type('#TPL_username_1',"asdasd")

await page.waitFor(1000)
await page.click('#su')

browser = await launch(headless=False, ignoreDefaultArgs=['--enable-automation'])
# 添加ignoreDefaultArgs=['--enable-automation'] 參數(shù)

from bs4 import BeautifulSoup
from pyppeteer import launch
import asyncio


def screen_size():
    return 1600,900


async def main(url):
    browser = await launch({"args":['--no-sandbox'],}) # "headless":False
    page = await browser.newPage()
    width, height = screen_size()
    await page.setViewport(viewport={'width':width,'height':height})
    await page.setJavaScriptEnabled(enabled=True)
    await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.77 Safari/537.36')
    await page.goto(url)

    await page.evaluate('window.scrollBy(0, document.body.scrollHeight)')

    await asyncio.sleep(1)

    # content = await page.content()
    li_list = await page.xpath('//*[@id="J_goodsList"]/ul/li')

    item_list = []
    for li in li_list:
        a = await li.xpath('.//div[@class="p-img"]/a')
        detail_url = await (await a[0].getProperty('href')).jsonValue()
        promo_words = await (await a[0].getProperty('title')).jsonValue()
        a_ = await li.xpath('.//div[@class="p-commit"]/strong/a')
        p_commit = await (await a_[0].getProperty('textContent')).jsonValue()
        i = await li.xpath('./div/div[3]/strong/i')
        price = await (await i[0].getProperty('textContent')).jsonValue()
        em = await li.xpath('./div/div[4]/a/em')
        title = await (await em[0].getProperty('textContent')).jsonValue()
        item = {
            "title" : title,
            "detail_url" : detail_url,
            "promp_words" : promo_words,
            "p_commit" : p_commit,
            "price" : price
        }
        item_list.append(item)

    await page_close(browser)
    return item_list


async def page_close(browser):
    for _page in await browser.pages():
        await _page.close()
    await browser.close()


url = 'https://search.jd.com/Search?keyword=%E6%89%8B%E6%9C%BA&wq='\
		'%E6%89%8B%E6%9C%BA&pvid=e07184578b8442c58ddd65b221020e99&page={}&s=56&click=0 '
task_list = []
for i in range(1,4):
    page = i * 2 - 1
    task_list.append(main(url.format(page)))

results = asyncio.get_event_loop().run_until_complete(asyncio.gather(*task_list))

for i in results:
    print(i,len(i))

print('*'*100)