快上网专注成都网站设计 成都网站制作 成都网站建设
成都网站建设公司服务热线:028-86922220

网站建设知识

十年网站开发经验 + 多家企业客户 + 靠谱的建站团队

量身定制 + 运营维护+专业推广+无忧售后,网站问题一站解决

Selenium爬取淘宝实战练习-创新互联

1、项目流程

成都创新互联主营庆云网站建设的网络公司,主营网站建设方案,app软件开发公司,庆云h5微信平台小程序开发搭建,庆云网站营销推广欢迎庆云等地区企业咨询

Selenium爬取淘宝实战练习

2、中心调度

# 中心调度

def main():

try:

total = search()

total = int(re.compile('.*?(d+).*?').search(total).group(1))

for i in range(2,total+1):

next_page(i)

except Exception as e:

print('异常')

finally:

browser.close()

3、模拟查询

# 根据关键字查询

def search():

try:

browser.get('https://www.taobao.com/')

# 直到搜索框加载出

input_search = wait.until(EC.presence_of_element_located((By.ID,'q')))

# 直到搜索按钮可以点击

submit_button = wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'btn-search')))

input_search.send_keys(KEYWORDS)

submit_button.click()

total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'div.wraper  div.total')))

get_products()

return total.text

except TimeoutException as e:

print('响应超时')

4、下一页的操作

# 下一页爬取

def next_page(index):

try:

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(index)

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(index)))

get_products()

except NoSuchElementException as e:

print('元素未加载')

return next_page(index)

5、商品信息的解析

# 获取一页上所有的商品

def get_products():

wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-itemlist .items .item")))

html = browser.page_source

doc = PyQuery(html)

items = doc('.m-itemlist .items  .item').items()

for item in items:

如果你感觉到学编程有些吃力,但是又对IT行业非常喜爱的话,可以加测试交流群:1017539290,进群免费领取测试学习资料!

product = {

'image':item.find('.pic-link .img').attr('data-src'),

'price':float(item.find('.price').text()[2:]),

'deal':item.find('.deal-cnt').text()[:-3],

'title':item.find('.title').text(),

'shop':item.find('.shop').text(),

'location':item.find('.location').text(),

'keywords':KEYWORDS

}

save_to_mongo(product=product)

6、完整代码

#!/usr/bin/python

# -*- coding: utf-8 -*-

import pymongo

import re

from pyquery import PyQuery

from selenium import webdriver

from selenium.webdriver.common.by import By

from selenium.webdriver.support.ui import WebDriverWait

from selenium.webdriver.support import expected_conditions as EC

from selenium.common.exceptions import TimeoutException,NoSuchElementException

from setting import *

client = pymongo.MongoClient(MONGO_HOST)

db = client[MONGO_DB]

browser = webdriver.Chrome()

wait = WebDriverWait(browser,10)

# 根据关键字查询

def search():

try:

browser.get('https://www.taobao.com/')

# 直到搜索框加载出

input_search = wait.until(EC.presence_of_element_located((By.ID,'q')))

# 直到搜索按钮可以点击

submit_button = wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'btn-search')))

input_search.send_keys(KEYWORDS)

submit_button.click()

total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'div.wraper  div.total')))

get_products()

return total.text

except TimeoutException as e:

print('响应超时')

# 下一页爬取如果你感觉到学编程有些吃力,但是又对IT行业非常喜爱的话,可以加测试交流群:1017539290,进群免费领取测试学习资料!

def next_page(index):

try:

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(index)

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(index)))

get_products()

except NoSuchElementException as e:

print('元素未加载')

return next_page(index)

# 获取一页上所有的商品

def get_products():

wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-itemlist .items .item")))

html = browser.page_source

doc = PyQuery(html)

items = doc('.m-itemlist .items  .item').items()

for item in items:

product = {

'image':item.find('.pic-link .img').attr('data-src'),

'price':float(item.find('.price').text()[2:]),

'deal':item.find('.deal-cnt').text()[:-3],

'title':item.find('.title').text(),

'shop':item.find('.shop').text(),

'location':item.find('.location').text(),

'keywords':KEYWORDS

}

save_to_mongo(product=product)

# 保存至mongoDB

def save_to_mongo(product):

try:

if db[MONGO_TABLE].insert(product):

print('保存成功', product)

except Exception:

print('保存失败')

# 中心调度

def main():

try:

total = search()

total = int(re.compile('.*?(d+).*?').search(total).group(1))

for i in range(2,total+1):

next_page(i)

except Exception as e:

print('异常')

finally:

browser.close()

if __name__=='__main__':

main()

7、运行结果

Selenium爬取淘宝实战练习


本文标题:Selenium爬取淘宝实战练习-创新互联
网站URL:http://6mz.cn/article/hoeij.html

其他资讯