第五次作业
作业①
爬取手机信息
要求：
熟练掌握 Selenium 查找HTML元素、爬取Ajax网页数据、等待HTML元素等内容。
使用Selenium框架爬取京东商城某类商品信息及图片。
候选网站：http://www.jd.com/
关键词：学生自由选择
输出信息：MYSQL的输出信息如下：
代码：
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import urllib.request
import threading
import sqlite3
import os
import datetime
from selenium.webdriver.common.keys import Keys
import time
class MySpider:
headers = {"User-Agent": "Mozilla/5.0 (Windows; U; Windows NT 6.0 x64; en-US; rv:1.9pre) Gecko/2008072421 Minefield/3.0.2pre"}
imagePath = "download"
def startUp(self, url, key):
# # Initializing Chrome browser
chrome_options = Options()
# chrome_options.add_argument('--headless')
# chrome_options.add_argument('--disable-gpu')
self.driver = webdriver.Chrome(options=chrome_options)
# Initializing variables
self.threads = []
self.No = 0
self.imgNo = 0
# Initializing database
try:
self.con = sqlite3.connect("phones.db")
self.cursor = self.con.cursor()
try:
# 如果有表就删除
self.cursor.execute("drop table phones")
except:
pass
try:
# 建立新的表
sql = "create table phones (mNo varchar(32) primary key, mMark varchar(256),mPrice varchar(32),mNote varchar(1024),mFile varchar(256))"
self.cursor.execute(sql)
except:
pass
except Exception as err:
print(err)
# Initializing images folder
try:
if not os.path.exists(MySpider.imagePath):
os.mkdir(MySpider.imagePath)
images = os.listdir(MySpider.imagePath)
for img in images:
s = os.path.join(MySpider.imagePath, img) #删除目录下的文件
os.remove(s)
except Exception as err:
print(err)
self.driver.get(url)
keyInput = self.driver.find_element_by_id("key")
keyInput.send_keys(key) #传入参数
keyInput.send_keys(Keys.ENTER) #回车键
def closeUp(self): #关闭数据库连接和浏览器驱动
try:
self.con.commit()
self.con.close()
self.driver.close()
except Exception as err:
print(err);
def insertDB(self, mNo, mMark, mPrice, mNote, mFile): #插入数据
try:
sql = "insert into phones (mNo,mMark,mPrice,mNote,mFile) values (?,?,?,?,?)"
self.cursor.execute(sql, (mNo, mMark, mPrice, mNote, mFile))
except Exception as err:
print(err)
def showDB(self): #数据库表的展示
try:
con = sqlite3.connect("phones.db")
cursor = con.cursor()
print("%-8s%-16s%-8s%-16s%s" % ("No", "Mark", "Price", "Image", "Note"))
cursor.execute("select mNo,mMark,mPrice,mFile,mNote from phones order by mNo")
rows = cursor.fetchall()
for row in rows:
print("%-8s %-16s %-8s %-16s %s" % (row[0], row[1], row[2], row[3], row[4]))
con.close()
except Exception as err:
print(err)
def download(self, src1, src2, mFile):
data = None
if src1:
try:
req = urllib.request.Request(src1, headers=MySpider.headers)
resp = urllib.request.urlopen(req, timeout=10)
data = resp.read()
except:
pass
if not data and src2:
try:
req = urllib.request.Request(src2, headers=MySpider.headers)
resp = urllib.request.urlopen(req, timeout=10)
data = resp.read()
except:
pass
if data:
print("download begin", mFile)
fobj = open(MySpider.imagePath + "\\" + mFile, "wb")
fobj.write(data)
fobj.close()
print("download finish", mFile)
def processSpider(self):
try:
time.sleep(1)
print(self.driver.current_url)
lis = self.driver.find_elements_by_xpath("//div[@id='J_goodsList']//li[@class='gl-item']")
for li in lis:
# We find that the image is either in src or in data-lazy-img attribute
try:
src1 = li.find_element_by_xpath(".//div[@class='p-img']//a//img").get_attribute("src")
except:
src1 = ""
try:
src2 = li.find_element_by_xpath(".//div[@class='p-img']//a//img").get_attribute("data-lazy-img")
except:
src2 = ""
try:
price = li.find_element_by_xpath(".//div[@class='p-price']//i").text
except:
price = "0"
try:
note = li.find_element_by_xpath(".//div[@class='p-name p-name-type-2']//em").text
mark = note.split(" ")[0]
mark = mark.replace("爱心东东\n", "")
mark = mark.replace(",", "")
note = note.replace("爱心东东\n", "")
note = note.replace(",", "")
except:
note = ""
mark = ""
self.No = self.No + 1
no = str(self.No)
while len(no) < 6:
no = "0" + no
print(no, mark, price)
if src1:
src1 = urllib.request.urljoin(self.driver.current_url, src1)
p = src1.rfind(".")
mFile = no + src1[p:]
elif src2:
src2 = urllib.request.urljoin(self.driver.current_url, src2)
p = src2.rfind(".")
mFile = no + src2[p:]
if src1 or src2:
T = threading.Thread(target=self.download, args=(src1, src2, mFile))
T.setDaemon(False)
T.start()
self.threads.append(T)
else:
mFile = ""
self.insertDB(no, mark, price, note, mFile)
try:
self.driver.find_element_by_xpath("//span[@class='p-num']//a[@class='pn-next disabled']")
except:
nextPage = self.driver.find_element_by_xpath("//span[@class='p-num']//a[@class='pn-next']")
time.sleep(10)
nextPage.click()
self.processSpider()
except Exception as err:
print(err)
def executeSpider(self, url, key):
starttime = datetime.datetime.now()
print("Spider starting......")
self.startUp(url, key)
print("Spider processing......")
self.processSpider()
print("Spider closing......")
self.closeUp()
for t in self.threads:
t.join()
print("Spider completed......")
endtime = datetime.datetime.now()
elapsed = (endtime - starttime).seconds
print("Total ", elapsed, " seconds elapsed")
url = "http://www.jd.com"
spider = MySpider()
while True:
print("1.爬取")
print("2.显示")
print("3.退出")
s = input("请选择(1,2,3):")
if s == "1":
spider.executeSpider(url, "手机")
continue
elif s == "2":
spider.showDB()
continue
elif s == "3":
break
运行结果部分展示：
心得体会
主要就是复现一下课上的代码，增加了解
实验②
爬取股票信息
要求：
熟练掌握 Selenium 查找HTML元素、爬取Ajax网页数据、等待HTML元素等内容。
使用Selenium框架+ MySQL数据库存储技术路线爬取“沪深A股”、“上证A股”、“深证A股”3个板块的股票数据信息。
候选网站：东方财富网：http://quote.eastmoney.com/center/gridlist.html#hs_a_board
输出信息：MYSQL数据库存储和输出格式如下，表头应是英文命名例如：序号id，股票代码：bStockNo……，由同学们自行定义设计表头：
代码：
from selenium import webdriver
from selenium.webdriver import ChromeOptions
from time import sleep
import pymysql
option = ChromeOptions()
option.add_experimental_option('excludeSwitches', ['enable-automation'])
driver = webdriver.Chrome(options=option)
driver.get("http://quote.eastmoney.com/center/gridlist.html#hs_a_board")
driver.maximize_window()
conn = None
cursor = None
conn = pymysql.Connect(host='127.0.0.1', port=3306, user='root', password='root', db='spider', charset='utf8')
cursor = conn.cursor()
modules = [ "hs_a_board","sh_a_board", "sz_a_board"] #遍历板块
for module in modules:
sleep(1)
driver.find_element_by_xpath('//*[@id="nav_{}"]'.format(module)).click() #板块点击
sleep(2)
driver.execute_script("var q=document.documentElement.scrollTop=10000") #下拉底部
while True:
trs = driver.find_elements_by_xpath('//*[@id="table_wrapper-table"]/tbody/tr')
for tr in trs:
id = tr.find_element_by_xpath("./td[1]").text
no = tr.find_element_by_xpath("./td[2]/a").text
name = tr.find_element_by_xpath("./td[3]/a").text
latest_price = tr.find_element_by_xpath("./td[5]/span").text
range = tr.find_element_by_xpath("./td[6]/span").text
amount = tr.find_element_by_xpath("./td[7]/span").text
trading = tr.find_element_by_xpath("./td[8]").text
transaction = tr.find_element_by_xpath("./td[9]").text
print(id, no, name, latest_price, range, amount, trading, transaction)
try:
cursor.execute('insert into stocks values("%s","%s","%s","%s","%s","%s","%s","%s")' %
(id, no, name, latest_price, range, amount, trading, transaction)) #插入数据
conn.commit()
except:
conn.rollback()
try:
driver.find_element_by_class_name("next paginate_button disabled")
except:
driver.find_element_by_xpath('//*[@id="main-table_paginate"]/a[@class="next paginate_button"]').click() #翻页
sleep(2)
driver.execute_script("var q=document.documentElement.scrollTop=0") #返回顶部
driver.quit()
cursor.close()
conn.close()
运行结果部分展示：
心得体会：
加深对selenium的了解程度
实验③
模拟登录mooc以及爬取课程信息
要求：
熟练掌握 Selenium 查找HTML元素、实现用户模拟登录、爬取Ajax网页数据、等待HTML元素等内容。
使用Selenium框架+MySQL爬取中国mooc网课程资源信息（课程号、课程名称、学校名称、主讲教师、团队成员、参加人数、课程进度、课程简介）
候选网站：中国mooc网：https://www.icourse163.org
输出信息：MYSQL数据库存储和输出格式：
代码：
from selenium import webdriver
from selenium.webdriver import ChromeOptions
from time import sleep
import pymysql
option = ChromeOptions()
option.add_experimental_option('excludeSwitches', ['enable-automation'])
driver = webdriver.Chrome(options=option)
driver.get("https://www.icourse163.org/")
driver.maximize_window()
sleep(2)
driver.find_element_by_xpath('//div[@class="unlogin"]//a[@class="f-f0 navLoginBtn"]').click() #登录或注册
sleep(2)
driver.find_element_by_class_name('ux-login-set-scan-code_ft_back').click() #其他登录方式
sleep(2)
driver.find_element_by_xpath("//ul[@class='ux-tabs-underline_hd']//li[@class='']").click()
sleep(2)
driver.switch_to.frame(driver.find_element_by_xpath("//div[@class='ux-login-set-container']//iframe"))
driver.find_element_by_xpath('//input[@id="phoneipt"]').send_keys("******") #输入账号
sleep(2)
driver.find_element_by_xpath('//input[@placeholder="请输入密码"]').send_keys("******") #输入密码
sleep(2)
driver.find_element_by_xpath('//div[@class="f-cb loginbox"]//a[@id="submitBtn"]').click() #点击登录
sleep(3)
driver.find_element_by_xpath(
'//div[@class="u-baseinputui"]/input[@class="j-textarea inputtxt"]').send_keys("python") #输入要找的课程
sleep(2)
driver.find_element_by_xpath('//div[@class="u-search-icon"]/span[@class="u-icon-search2 j-searchBtn"]').click() #点击搜索
sleep(2)
conn = None
cursor = None
conn = pymysql.Connect(host='127.0.0.1', port=3306, user='root', password='root', db='spider', charset='utf8')
cursor = conn.cursor()
id=0
while True:
sleep(2)
divs = driver.find_elements_by_xpath('//div[@class="m-course-list"]/div/div')
for i in range(len(divs)):
try:
div = driver.find_elements_by_xpath('//div[@class="m-course-list"]/div/div')[i + 1]
div.click()
sleep(3)
current_window = driver.window_handles[-1] #切换到最新打开的页面
driver.switch_to.window(current_window)
sleep(2)
id += 1
course = driver.find_element_by_xpath('//span[@class="course-title f-ib f-vam"]').text
process = driver.find_element_by_xpath(
'//div[@class="course-enroll-info_course-info_term-info_term-time"]/span[2]').text
college = driver.find_element_by_xpath('//*[@id="j-teacher"]/div/a/img').get_attribute("alt")
count = driver.find_element_by_xpath(
'//span[@class="course-enroll-info_course-enroll_price-enroll_enroll-count"]').text
brief = driver.find_element_by_xpath('//*[@id="j-rectxt2"]').text
teacher = driver.find_element_by_xpath('//div[@class="cnt f-fl"][1]/h3').text
team = ""
teas = driver.find_elements_by_xpath('//div[@class="um-list-slider_con"]/div')
if len(teas)>1:
for tea in teas:
team = team + tea.find_element_by_xpath('.//div[@class="cnt f-fl"]/h3').text #教师拼接
else:
team=teacher
print(course, college, teacher, team, process, brief)
try:
cursor.execute('insert into mooc values("%s","%s","%s","%s","%s","%s","%s","%s")' %
(id, course, college, teacher, team, count, process, brief)) # 插入数据
conn.commit()
except:
conn.rollback()
driver.close()
sleep(2)
previous_window = driver.window_handles[0] #切换回最开始打开的界面
sleep(2)
driver.switch_to.window(previous_window)
sleep(2)
try:
driver.find_element_by_xpath(
'//li[@class="ux-pager_btn ux-pager_btn__next"]/a[@class="th-bk-disable-gh"]')
except:
driver.find_element_by_xpath(
'//li[@class="ux-pager_btn ux-pager_btn__next"]/a[@class="th-bk-main-gh"]').click()
sleep(3)
except Exception as e:
print(e)
driver.quit()
cursor.close()
conn.close()
运行结果部分展示：
心得体会：
遇到了问题：Message: stale element reference: element is not attached to the page document
divs = driver.find_elements_by_xpath('//div[@class="m-course-list"]/div/div')
for div in divs:
div.click()
...
这样就容易点击了第一个div之后，页面出现刷新的情况，再想点第二个就会报这个错
可以改成：
divs = driver.find_elements_by_xpath('//div[@class="m-course-list"]/div/div')
for i in range(len(divs)):
driver.find_element_by_xpath('//a[@class="class name"][i+1]').click()
需要在页面刷新后重新定位再进行操作。
