爬虫学习-第二十篇

"""
Version: 0.1
Author: freshbin
Date: 2019年8月30日
"""

print("=================================selenium爬取淘宝商品信息 start================================================")

from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from urllib.parse import quote

"""
chrine_options = webdriver.ChromeOptions()
chrine_options.add_argument('--headless')
browser = webdriver.Chrome(chrome_options=chrine_options)
"""

browser = webdriver.Chrome()
wait = WebDriverWait(browser, 10)
KEYWORD = 'ipad'

header = {
    'referer': 'https://s.taobao.com/',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'none',
    'sec-fetch-user': '?1',
    'upgrade-insecure-requests': 1,
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36'
}

def index_page(page):
    """
    抓取索引页
    :param page: 页码
    :return:
    """
    print('正在爬取第', page, '页')
    try:
        url = 'https://s.taobao.com/search?q=' + quote(KEYWORD) + '&initiative_id=staobaoz_20190830'
        # print('访问的url:', url)
        browser.get(url)
        if page > 1:
            input = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager div.form > input')))
            submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#mainsrp-pager div.form > span.btn.J_Submit')))
            input.clear()
            input.send_keys(page)
            submit.click()
        EC.text_to_be_present_in_element((By.CSS_SELECTOR, '#mainsrp-pager li.item.active > span'), str(page))
        wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.m-itemlist .items .item')))
        get_products()
    except TimeoutException:
        index_page(page)
from pyquery import PyQuery as pq
def get_products():
    """
    提取商品数据
    :return:
    """
    html = browser.page_source
    doc = pq(html)
    items = doc('#mainsrp-itemlist .items .item').items()
    for item in items:
        product = {
            'image': item.find('.pic .img').attr('data-src'),
            'price': item.find('.price').text(),
            'deal': item.find('.deal-cnt').text(),
            'title': item.find('.title').text(),
            'shop': item.find('.shop').text(),
            'location': item.find('.location').text()
        }
        print(product)
        save_to_mongo(product)

import pymongo
MONGO_URL = 'localhost'
MONGO_DB = 'taobao'
MONGO_COLLECTION = 'products'
client = pymongo.MongoClient(MONGO_URL)
db = client[MONGO_DB]
def save_to_mongo(result):
    """
    保存至MongoDB
    :param result:
    :return:
    """
    try:
        if db[MONGO_COLLECTION].insert(result):
            print('存储到MongoDB成功')
    except Exception:
        print('存储到MongoDB失败')

MAX_PAGE = 100
def main():
    """
    遍历每一页
    :return:
    """
    for i in range(1, MAX_PAGE + 1):
        index_page(i)

if __name__ == '__main__':
    main()
print("=================================selenium爬取淘宝商品信息 end================================================")