使用selenium模拟浏览器抓取淘宝信息

通过Selenium模拟浏览器抓取淘宝商品美食信息，并存储到MongoDB数据库中。

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
from pyquery import PyQuery as pq
import re
import json
from config import *
import pymongo
client = pymongo.MongoClient(MONGO_URL)
db = client[MONGO_DB]
browser = webdriver.Firefox()
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(‘美食‘)
        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):
    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:
        return next_page(page_number)

# def write_to_file(content):
#     with open(‘E:/python/Projects/test1/result.txt‘,‘a‘,encoding=‘utf-8‘) as f:
#         f.write(json.dumps(content,ensure_ascii=False) + ‘\n‘)
#         f.close()

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 )
        # write_to_file(product)
def save_to_mongo(result):
    try:
        if db[MONGO_TABLE].insert(result):
            print(‘存储到MONGODB成功‘,result)
    except Exception:
        print(‘存储到MONGODB失败‘,result)

def main():
    total= search()
    total = int(re.compile(‘(\d+)‘).search(total).group(1))
    for i in range(2,total+1):
        next_page(i)
    browser.close()
if __name__ == ‘__main__‘:
    main()

原文地址：https://www.cnblogs.com/ls-pankong/p/12287012.html