流程框架

• 搜索關鍵字，利用selenium驅動瀏覽器搜索關鍵字
• 分析頁碼并翻頁，得到商品頁碼數(shù)，模擬翻頁，得到后續(xù)頁碼的商品列表
• 分析提取商品內(nèi)容，利用PyQuery分析源碼，解析得到商品列表
• 存儲至MongoDB，將商品列表信息存儲到數(shù)據(jù)庫

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 selenium.common.exceptions import TimeoutException
from bs4 import BeautifulSoup
import json

broswer = webdriver.Chrome()
wait = WebDriverWait(broswer, 10)

def search():
    try:
        broswer.get('https://www.jd.com')
        input = wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR, '#key'))
        )
        submit = wait.until(
            EC.element_to_be_clickable((By.CSS_SELECTOR, '#search > div > div.form > button')) 
        )
        input.send_keys('口罩')
        submit.click()
        total = wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR, '#J_bottomPage > span.p-skip > em:nth-child(1) > b'))
        ) 
        get_products()
        return total.text
    except TimeoutException:
        return search()

def next_page(pager_number):
    try:
        input = wait.until(
                EC.presence_of_element_located((By.CSS_SELECTOR, '#J_bottomPage > span.p-skip > input'))
            )
        submit = wait.until(
                EC.element_to_be_clickable((By.CSS_SELECTOR, '#J_bottomPage > span.p-skip > a')) 
            )
        input.clear()
        input.send_keys(pager_number)
        submit.click()
        wait.until(EC.text_to_be_present_in_element(
            (By.CSS_SELECTOR,'#J_bottomPage > span.p-num > a.curr'), str(pager_number))
                  )
        get_products()
    except TimeoutException:
        return next_page(pager_number)   

def get_products():
    wait.until(
            EC.presence_of_element_located((By.CSS_SELECTOR, '#J_bottomPage > span.p-skip > em:nth-child(1) > b'))
        ) 
    html = broswer.page_source
    soup = BeautifulSoup(html, 'lxml')
    titles = soup.select('.gl-item .p-name.p-name-type-2 a em')
    urls = soup.select('.gl-item .p-img a')
    
    for title, url in zip(titles, urls):
        product = {
            'title':title.get_text(),
            'url':url['href']
        }
        write_to_file(product)
        print(product)

def write_to_file(product):
    with open('JD_product.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(product, ensure_ascii=False) + '\n')
        f.close

def main():
    total = int(search())
    for i in range(2, total+1):
        next_page(i)
    broswer.close()

if __name__ == '__main__':
    main()