淘宝爬虫

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait
from selenium.common.exceptions import TimeoutException
from pyquery import PyQuery as pq
import re
from config import *
import pymongo

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

wait = WebDriverWait(browser, 10)


def search():
    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('xiaomi')
        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_num):
    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_num)
        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_num)))
        get_products()
    except TimeoutException:
        next_page(page_num)

def get_products():
    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .items .item')))
    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('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()

        }
        print(product)
        save_to_mongo(product)

def save_to_mongo(result):
    try:
        if db[MONGO_TABLE].insert(result):
            print('success save to mongodb', result)
    except Exception:
        print('error to mongo')

def main():
    total = search()
    total = int(re.compile('(d+)').search(total).group(1))
    # print(total)
    for i in range(2, total):
        next_page(i)
    browser.close()

if __name__ == '__main__':
    main()

 config.py

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

 

运行结果：

 数据库：