Python使用Selenium模块实现模拟浏览器抓取淘宝商品美食信息功能

本文实例讲述了Python使用Selenium模块实现模拟浏览器抓取淘宝商品美食信息功能。分享给大家供大家参考，具体如下：

import refrom selenium import webdriverfrom selenium.webdriver.common.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom selenium.common.exceptions import TimeoutExceptionfrom pyquery import PyQuery as pqfrom bs4 import BeautifulSoupfrom pymongo import MongoClientfrom pymongo.errors import PyMongoErrorurl = 'http://www.taobao.com'KEYWORD = '美食'# monogdb配置信息MONGO_HOST = "localhost"MONGO_DATABASE = "taobao"MONGO_TABLE = "meishi"client = MongoClient(host=MONGO_HOST)db = client[MONGO_DATABASE]# PhantomJS 命令行相关配置# 参见 http://phantomjs.org/api/command-line.htmlSERVICE_ARGS = ['--disk-cache=true', '--load-images=false']# driver = webdriver.Chrome() # 有界面driver = webdriver.PhantomJS(service_args=SERVICE_ARGS) # 无界面delay = 10wait = WebDriverWait(driver, delay)# print('windows size', driver.get_window_size())# PhantomJs()的浏览器窗口很小,宽高只有400 * 300driver.maximize_window() # 窗口最大化 # 对于PhantomJS来说设置窗口大小很关键，如果不设置，经常会出现问题# driver.set_window_size(1920, 1080) # 设置浏览器窗口大小# 模拟在淘宝网页中输入关键字搜索def search():  print("准备搜索 %s" % KEYWORD)  try:    driver.get(url)    input_box = wait.until(      EC.presence_of_element_located((By.CSS_SELECTOR, "input#q"))    )    search_btn = wait.until(EC.element_to_be_clickable(      (By.CSS_SELECTOR, '#J_TSearchForm > div.search-button > button')))    input_box.send_keys(KEYWORD)    search_btn.click()    total_page_str = wait.until(      EC.presence_of_element_located(        (By.CSS_SELECTOR, 'div.total'))).text    total_page_num = int(re.search("(/d+)", total_page_str).group(1))    item_list = get_goods_by_beautifulsoup()    save_to_mongodb(item_list)    return total_page_num  except TimeoutError:    print("搜索%s超时", KEYWORD)    print("重新尝试搜索: %s", KEYWORD)    search()# 根据页码获取指定页数据，并将其保存到数据库中def get_page(page_num):  print("正在获取第%d页数据" % page_num)  try:    page_num_box = wait.until(      EC.presence_of_element_located(        (By.CSS_SELECTOR, "div.form > input")))    ok_btn = wait.until(EC.element_to_be_clickable(      (By.CSS_SELECTOR, 'div.form > span.btn.J_Submit')))    page_num_box.clear()    page_num_box.send_keys(page_num)    ok_btn.click()    wait.until(      EC.text_to_be_present_in_element(        (By.CSS_SELECTOR,         'li.item.active > span.num'),        str(page_num)))    item_list = get_goods_by_beautifulsoup()    save_to_mongodb(item_list)  except TimeoutException:    print("请求第%d页失败" % page_num)    print("尝试重新获取第%d页" % page_num)    return get_page(page_num)def get_goods_by_pyquery():  '''  通过pyquery库解析数据  获取商品的图片url、价格、标题、成交量、店铺名称、店铺位置  '''  wait.until(EC.presence_of_element_located(    (By.CSS_SELECTOR, "#mainsrp-itemlist .items .item")))  html = driver.page_source  doc = pq(html)  items = list(doc('#mainsrp-itemlist .items .item').items())  for item in items:    yield {      # 不要用src属性,获取的图片地址很多是.gif图片，而非真实商品图片,      'image': 'http://' + item.find('.J_ItemPic.img').attr('data-src'),      'price': item.find('.price').text(),      'title': item.find('.row > .J_ClickStat').text().strip(),      'deal_cnt': item.find('.deal-cnt').text()[:-3],      'shop': item.find('.shop').text(),      'location': item.find('.location').text(),    }# 通过bs4解析数据def get_goods_by_beautifulsoup():  '''  通过bs4库解析数据  获取商品的图片url、价格、标题、成交量、店铺名称、店铺位置  '''  wait.until(EC.presence_of_element_located(    (By.CSS_SELECTOR, "#mainsrp-itemlist .items .item")))  html = driver.page_source  soup = BeautifulSoup(html, 'lxml')  items = soup.select('#mainsrp-itemlist .items .item')  for item in items:    yield {      'image': 'http:' + item.select('img.J_ItemPic.img')[0]['data-src'],      'price': item.select('div.price.g_price.g_price-highlight')[0].get_text(strip=True),      'title': item.select('div.row.row-2.title > a.J_ClickStat')[0].get_text(strip=True),      'deal_cnt': item.select('div.deal-cnt')[0].text[:-3],      'shop': item.select('div.shop > a')[0].get_text(strip=True),      'location': item.select('div.location')[0].text,    }def save_to_mongodb(item_list):  for item in item_list:    try:      db[MONGO_TABLE].insert(item)  # insert支持插入多条数据      print("mongodb插入数据成功:", item)    except PyMongoError as e:      print("mongodb插入数据失败:", item, e)# 获取淘宝美食的图片url、价格、标题、成交量、店铺名称、店铺位置并将结果保存在mongodb数据库中if __name__ == '__main__':  try:    total_pages = search()    for page_num in range(2, total_pages + 1):      get_page(page_num)  except Exception as e:    print("出错了", e)  finally: # 确保 浏览器能正常关闭    driver.close()