python爬虫之pyppeteer库简单使用

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

# pyppeteer支持字典和关键字传参
browser = await launch({'headless':True})
browser = await launch(headless=True)

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

# pyppeteer使用python风格的函数名
page.querySelector()/page.querySelectorAll()/page.xpath()

# 简写方式
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参数设置为Falase，则变成有头模式
    browser = await launch(headless=False, ignoreDefaultArgs=['--enable-automation'])
    page = await browser.newPage()
    
    # 设置页面视图大小
    await page.setViewport(viewport={'width':1600,'herght':900})
    
    # 是否启用JS，enabled设为False，则无渲染效果
    await page.setJavaScriptEnable(enabled=True)
    
    # 等待时间1000毫秒
    res = await page.goto(url，options={'timeout':1000})
    resp_headers = res.headers  # 响应头
    resp_status = res.status    # 响应状态
    
    # 等待
    await asyncio.sleep(2)
    await page.waitFor(1000)
    # 第二种方法 ，在while循环里强行查询某元素进行等待
    while not await page.querySelector('.t')
    
    # 滚动到页面底部
    await page.evaluate('window.scrollBy(0,document.body.scrollHeight)')
    
    await page.screenshot({'path':'test.png'})
    
    # 打印网页cookies
    print(await page.cookies())
    
    # 获取所有html内容
    print(await page.content())
    
    
    dimensions = await page.evaluate(pageFunction='''() => {
    		return {
    			width:document.documentElement.clentWidth,    // 页面宽度
    			height:document.documentElement.clentHeight,  // 页面高度
    			deviceScaleFactor: window.devicePixelRatio,  // 像素比1.0000000149011612
    			}
    		}''',force_expr=False)   # force_expr=False  执行的是函数
    print(dimensions)
    
    content = await page.evaluate(pageFunction='document.body.textContent',force_expr=True)    # 只获得文本 执行js脚本，force_expr=True  执行的是表达式
    print(content)
    
    # 打印当前页面的标题
    print(await page.title())
    
    
    # 抓取新闻内容  可以使用xpath表达式
    '''
    pyppeteer 三种解析方式
    page.querySelector()
    page.querySelectorAll()
    page.xpath()
    简写方式为：
    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'))
        # 获取文本内容
        title_str = await (await item.getProperty('textContent')).jsonValue()
        
        title_link = await (await item.getProperty('textContent')).jsonValue()
        
        # 获取属性值
        # title = await (await item.getProperty('class')).jsonValue()
        print(title_str,title_link)
    await browser.close()


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

# 模拟输入账号密码 参数{'delay':reand_int()}  延迟输入时间
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'] 参数

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)