selenium的使用

引入，可以参考selenium的api

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
import re
import time
from pyquery import PyQuery as pq
import pymongo

连接mongodb数据库

hostName = 'localhost'
databaseName = 'taobao'
tableName = 'taobao'
port = 27017
client = pymongo.MongoClient(hostName, port)
db = client[databaseName]
tb = db[tableName]

配置全局的浏览器

# 拿到css选择器  copy  -》 copy selector
browser = webdriver.Chrome()
wait = WebDriverWait(browser, 10)

定义首次搜索方法

def search():  # 处理第一个页面
    try:  # 需要处理Timeout异常
        browser.get("https://www.taobao.com/")
        # 拿到输入框
        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#q")))
        # 拿到搜索按钮
        submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, "#J_TSearchForm > div.search-button > button")))
        input.send_keys('美食')
        submit.click()
        # 获取页数
        total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.total")))
        get_product()
        return total.text
    except TimeoutException:
        return search()  # 递归的去进行查询

定义后续的搜索方法

def next_page(page_number):  # 处理第二个往后的页面
    try:  # 需要处理Timeout异常
        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()
        # text_to_be_present_in_element  # 指定节点是否包含当前元素
        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_product()
    except TimeoutException:
        next_page(page_number)

页面展示出来之后，拿到网页源代码，并使用PyQuery进行抓取

def get_product():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-itemlist .items .item")))
    html = browser.page_source  # 拿到网页源代码
    doc = pq(html)  # 传入html，得到dom节点
    items = doc('#mainsrp-itemlist .items .item').items()  # 调用items方法，得到所有选择的内容
    for item in items:
        product = {
            'image': item.find('.pic .img').attr('src'),
            'price': item.find('.price').text(),
            'deal': item.find('.deal-cnt').text()[:-3],
            'title': item.find('.title').text(),
            'shop': item.find('.shop').text(),
            'location': item.find('.location').text()
        }
        print(product)
        tb.insert(product)