python爬虫——淘宝爬取

墨蓝 2021-07-26 16:07 779阅读 0赞

## python爬虫爬取淘宝商品信息 ##

**话不多说，直接上代码！**

import re
    from selenium import webdriver
    from selenium.webdriver.common.by import By
    from selenium.webdriver.support.ui import WebDriverWait
    from selenium.webdriver.support import expected_conditions as EC
    from pyquery import PyQuery as pq
    
    browser = webdriver.Chrome()
    wait = WebDriverWait(browser, 10)
    
    def search():
        try:
            url = "https://www.taobao.com"
            browser.get(url)
            input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#q")))
            submit = wait.until(
                EC.element_to_be_clickable((By.CSS_SELECTOR, '#J_TSearchForm > div.search-button > button')))
            input.send_keys('美食')
            submit.click()
            total = wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.total')))
            get_products()
            return total.text
        except:
            search()
    
    def next_page(page_number):
        try:
            input = wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > input")))
            submit = wait.until(EC.element_to_be_clickable(
                (By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit')))
            input.clear()
            input.send_keys(page_number)
            submit.click()
            wait.until(EC.text_to_be_present_in_element(
                (By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > ul > li.item.active > span'), str(page_number)))
            get_products()
        except:
            next_page(page_number)
    
    def get_products():
        html = browser.page_source
        doc = pq(html)
        items = doc('#mainsrp-itemlist .items .item').items()  # 得到所有宝贝的内容
        for item in items:
            product = { 
                'image': item.find('.pic .img').attr('data-src'),  # 图片链接
                'price': item.find('.price').text(),  # 商品价格
                'deal': item.find('.deal-cnt').text()[:-3],  # 付款人数，-3是为了去掉人付款这几个字
                'title': item.find('.title').text(),  # 商品名称
                'shop': item.find('.shop').text(),  # 店铺名称
                'location': item.find('.location').text()
            }
            print(product)
    
    def main():
        total = search()
        total = int(re.compile('(\d+)').search(total).group(1))  # 转换为数值型
        print(total)
        for i in range(2, total + 1):
            next_page(i)
    
    if __name__ == '__main__':
        main()

**运行结果：**  
![在这里插入图片描述][watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2d1b3h1eWluZw_size_16_color_FFFFFF_t_70_pic_center]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L2d1b3h1eWluZw_size_16_color_FFFFFF_t_70_pic_center]: /images/20210726/ddd35f9f803c403d94353d87c9497b72.png