selenium模拟浏览器爬取淘宝产品信息

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
from pyquery import PyQuery
from day01.config import *
import pymongo
client = pymongo.MongoClient(MONGO_URL) #连接mongodb
db = client[MONGO_DB]

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

def search():
    try:
        browser.get("https://www.taobao.com")
        # 输入框
        input_box = 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_box.send_keys("美食")
        submit.click()
        login = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#fm-login-id")))
        if login is not None:
            login.send_keys("********")
            password = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#fm-login-password")))
            password.send_keys("*********")
            login_button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"#login-form > div.fm-btn > button")))
            login_button.click()
        else:
            pass
        total_page = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > div.total")))
        get_products()
        return total_page.text
    except TimeoutException:
        return search()
    # finally:
    #     browser.quit()

def next_page(page_number):
    "操作翻页"
    try:
        input_page = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > div.form > input")))
        confirm_button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit")))
        input_page.clear()
        input_page.send_keys(page_number)
        confirm_button.click()
        # 判断页码数是否在当前页,用来判断元素中存在指定文本的
        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 TimeoutException:
        next_page(page_number)

def get_products():
    "获取产品信息"
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,"#mainsrp-itemlist .items .item")))
    html = browser.page_source #可以返回网页源码
    doc = PyQuery(html) #使用pyquery解析网页
    items = doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product = {
            'image':item.find('.pic .img').attr('src'),#获取标签属性
            'price':item.find('.price').text(), #价格
            'deal':item.find('.deal-cnt').text()[:-3], #成交量
            'title':item.find('.title').text(),
            'shop':item.find('.shop').text(),
            'location':item.find('.location').text()
        }
        # print(product)
        save_to_mongo(product)
        # from day01.connectMongo import ConnectMongo
        # con = ConnectMongo()
        # con.insert_one_data(product,"table")

def save_to_mongo(result):
    try:
        if db[MONGO_TABLE].insert(result):
            print("存储到mongodb成功")
    except Exception as e:
        print("存储到mongodb异常，%s"%e)


def main():
    result = search()
    total = int(re.compile("(d+)").search(result).group(1))
    for i in range(2,total+1):
        next_page(i)

if __name__ == '__main__':
    main()