python 爬取 js渲染_Python爬虫学习笔记7：动态渲染页面爬取
淘宝，它的整个页面数据确实也是通过 Ajax获取的，但是这些 Ajax接口 参数比较复杂，可能会包含加密密钥等， 所以如果想自己构造 Ajax 参数，还是比较困难的 。 对于这 种页面 ， 最方便快捷 的抓取方法就是通过 Selenium
商品列表信息
# 爬取淘宝页面商品信息，包括商品名称、商品价格、购买人数、店铺名称、店铺所在地
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
from pyquery import PyQuery as pq
import json
browser = webdriver.Chrome()
wait = WebDriverWait(browser,10)
KEYWORD = 'iPad'
def index_page(page):
print('正在爬取第',page,'页')
try:
url = 'https://www.taobao.com/search?q=' + quote(KEYWORD)
browser.get(url)
if page > 1: # 如果大于1，就进行跳转操作，否则等待页面加载完成
input = wait.until(
EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-pager div.from>input'))
)
submit = wait.until(
EC.element_to_be_clickable((By.CSS_SELECTOR,'#mainsrp-pager div.from>span.btn.J_Submit'))
)
input.clear()
input.send_keys(page)
submit.click()
wait.until(
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)
def get_products():
taobao_data = []
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('.title').text(),
'shop': item.find('.shop').text(),
'location': item.find('.location').text()
}
print(product)
taobao_data.append(product)
with open('taobao.json','a',encoding='utf-8') as f:
f.write(json.dumps(taobao_data, indent=2, ensure_ascii=False))
# MONGO_URL = 'localhost'
# MONGO_DB = 'taobao'
# MONGO_COLLECTION = 'products'
# client = pymongo.MongoClient(MONGO_URL)
# db = client[MONGO_DB]
#
# def save_to_mongo(result):
# try:
# if db[MONGO_COLLECTION].insert(result):
# print('存储到MongoBD 成功')
# except Exception:
# print('存储到MongoBD 失败')
MAX_PAGR = 100
def main():
for i in range(1,MAX_PAGR+1):
index_page(i)
main()
测试代码跑起来了，不过提示页面找不到了，没爬取成功，后面在补充学习
