selenium+phantomjs+pyquery 爬取淘宝商品信息

from selenium import webdriver
from selenium.common.exceptions import TimeoutException
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 pyquery import PyQuery as pq
from config import *
import pymongo

client = pymongo.MongoClient(MONGO_URL)
db =client[MONGO_DB]

browser = webdriver.PhantomJS(service_args=SERVICE_ARGS)
wait = WebDriverWait(browser, 10)# 等待时长10秒，默认0.5秒询问一次，等待页面加载完成，找到某个条件发生后再继续执行后续代码，如果超过设置时间检测不到则抛出异常
browser.set_window_size(1400,900)
def search():
    print("正在搜索")
    try:
        browser.get('https://www.taobao.com/')
        input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#q")))#模拟输入框
        submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,"#J_TSearchForm > div.search-button > button")))
        #模拟搜索按钮
        input.send_keys('美食')#添加input
        submit.click()#模拟按下搜索按钮
        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()
def next_page(page_number):#翻页，把当前页码清除后，直接跳转到想去的页码
    print("正在翻页",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_product()
    except TimeoutException:
        next_page(page_number)
def get_product():#获得每页商品内容，pyquery not understand
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-itemlist .items .item")))
    html =browser.page_source
    # print(html)
    doc = pq(html)
    items = doc("#mainsrp-itemlist .items .item").items()#注意class名字后空格！
    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()#find 查找的是div class的名字 别的标签不可以
        }
        print(product)
        save_to_mongo(product)
def save_to_mongo(result):#将数据存储到mongodb
    try:
        if db[MONGO_TABLE].insert(result):
            print('存储成功->',result)
    except Exception:
        print('存储失败->',result)
def main():
    total = search()
    total = int(re.compile('\d+').search(total).group(0))
    for i in range(2,20):
        next_page(i)
    browser.close()

if __name__ == '__main__':
    main()

---

MONGO_URL = 'localhost'
MONGO_DB = 'taobao'
MONGO_TABLE = 'product'

SERVICE_ARGS  = ['--load-images=false', '--disk-cache=true']

---