实战2：使用selenium爬取淘宝数据，保存在mongodb

配置文件

MONGO_URL = 'localhost'
MONGO_DB = 'taobao'
MONGO_TABLE = 'yintiao'

爬虫文件

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, connect=False)
db = client[MONGO_DB]


options = webdriver.ChromeOptions()
options.add_argument('--headless')
options.add_argument('--disable-gpu')
browser=webdriver.Chrome(options=options)
wait = WebDriverWait(browser, 10)

def search(keyword):
    print('正在搜索')
    try:
        browser.get('https://www.taobao.com')
        input = 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.send_keys(keyword)
        submit.click()
        total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-pager > div > div > div > div.total')))
        get_products()
        return total.text
    except TimeoutException:
        return search()

def next_page(page_number):
    print('翻页到',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_products()
    except TimeoutException:
        next_page(page_number)

def get_products():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .items .item')))
    html = browser.page_source#得到浏览器当前网页源代码
    doc = pq(html)
    items = doc('#mainsrp-itemlist .items .item').items() #items()方法返回一个生成器，生成器逐一返回该pyquery对象内的所有pyquery对象
    for item in items:
        product = {
            'image': item.find('.pic .img').attr('src'),
            'price': item.find('.price').text(),
            #'deal': item.find('deal-cnt').text(),
            'deal': re.compile('(\d+)').search(item.find('.deal-cnt').text()).group(1),
            'title': item.find('.title').text(),
            'shop': item.find('.shop').text(),
            'lication': item.find('.location').text()
        }
        print(product)
        save_to_mongo(product)
def save_to_mongo(result):
    try:
        if db[MONGO_TABLE].insert(result):
            print('save to mongodb success', result)
    except Exception:
        print('save to mongodb false!')
def main():
    try:
        total = search('银条')
        total = int(re.compile('(\d+)').search(total).group(1))
        #print(total)
        for i in range(2,total+1):
            next_page(i)
    except Exception:
        print('main error')
    finally:
        browser.close()

if __name__ == '__main__':
    main()