python 爬取淘宝商品

ゝ一纸荒年。 2022-05-20 10:15 370阅读 0赞

#coding:utf-8
    from selenium import webdriver
    from selenium.common.exceptions import TimeoutException
    from selenium.webdriver.common.by import By
    from selenium.webdriver.support import expected_conditions as EC
    from selenium.webdriver.support.wait import WebDriverWait
    from pyquery import PyQuery as pq
    from urllib.parse import quote
    import json
    
    #---------------配置webdriver加载浏览器不会弹出----------------------------
    chrome_options = webdriver.ChromeOptions()
    chrome_options.add_argument('--headless')
    browser = webdriver.Chrome(chrome_options=chrome_options)
    
    
    #---------------显示等待时间--------------------------
    wait = WebDriverWait(browser, 10)
    #client = pymongo.MongoClient(MONGO_URL)
    #db = client[MONGO_DB]
    
    
    h=open('taobao.txt','a',encoding='utf-8')
    
    def index_page(page):
        print('正在爬取第', page, '页')
        try:
            url = 'https://s.taobao.com/search?q=' + quote('ipad') #----------------------可以更改商品
            print (url)
            browser.get(url)
            if page > 1:
                input = wait.until(
                    EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager div.form > input')))  #寻找输入框以及按钮
                submit = wait.until(
                    EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager div.form > span.btn.J_Submit')))
                input.clear()
                input.send_keys(page)
                submit.click()
            wait.until(
                EC.text_to_be_present_in_element((By.CSS_SELECTOR, '#mainsrp-pager li.item.active > span'), str(page)))   #判断高亮
            wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.m-itemlist .items .item')))
            get_products()
        except TimeoutException:
            index_page(page)
    
    
    def get_products():
        html = browser.page_source
        doc = pq(html)
        items = doc('#mainsrp-itemlist .items .item').items()
        for item in items:
            product = {
                'image': item.find('.pic .img').attr('data-src'),
                'price': item.find('.price').text(),
                'deal': item.find('.deal-cnt').text,
                'title': item.find('.title').text(),
                'shop': item.find('.shop').text(),
                'location': item.find('.location').text()
            }
            print(product)
            save(product)
    
    
    def save(result):
        h.write(str(result))
    def main():
        for i in range(1, 3):#--------------可以更改页数
            index_page(i)
        browser.close()
    
    
    if __name__ == '__main__':
        main()

需要安装相关包。