美文网首页
selenium爬取淘宝商品

selenium爬取淘宝商品

作者: xin激流勇进 | 来源:发表于2018-07-30 10:27 被阅读0次
    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
    import re
    from bs4 import BeautifulSoup
    import json
    
    
    browser = webdriver.Chrome()
    wait = WebDriverWait(browser, 10)
    
    
    def search():
        try:
            browser.get('https://www.taobao.com/')
            input = wait.until(EC.presence_of_element_located((By.ID, '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():
        wait.until((EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist'))))
        soup = BeautifulSoup(browser.page_source, 'lxml')
        for item in soup.find('div', {'id': 'mainsrp-itemlist'}).find_all('div', {'class': 'item'}):
            title = item.select_one('.title').text.strip()
            price = item.select_one('.price').find('strong').text
            location = item.select_one('.location').text
            product = {'title': title, 'price': price, 'location': location}
            print(product)
            # print(len(soup.find('div', {'id': 'mainsrp-itemlist'}).find_all('div', {'class': 'item'})))
            save_to_file(product)
            # json.dump(product, file)
            # print(file)
    
    def save_to_file(data):
        file = open('data.txt', 'a')
        json.dump(data, file)
        file.close()
    
    
    def main():
        file = open('data.txt', 'w')
        total = search()
        # total = int(re.compile('(\d+)').search(total).group(1))
        for i in range(2, 4):
            next_page(i)
        browser.close()
        file.close()
    
    
    if __name__ == '__main__':
        main()
    

    相关文章

      网友评论

          本文标题:selenium爬取淘宝商品

          本文链接:https://www.haomeiwen.com/subject/idbxvftx.html