作业①:
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。
输出信息：MYSQL的输出信息如下
| mNo | mMark | mPrice | mNote | mFile |
| 000001 | 三星Galaxy | 9199.00 | 三星Galaxy Note20 Ultra 5G... | 000001.jpg |
| 000002 | ... | ... | ... | ... |
1)代码:
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
import urllib.request
import threading
import sqlite3
import os
import pymysql
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(chrome_options=chrome_options)
# Initializing variables
self.threads = []
self.No = 0
self.imgNo = 0
# Initializing database
try:
self.con = pymysql.connect(host="127.0.0.1", port=3306, user="root",
passwd="root", db="crawler", charset="utf8")
self.cursor = self.con.cursor(pymysql.cursors.DictCursor)
try:
# 如果有表就删除
self.cursor.execute("drop table phones if table exist")
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)
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)
keyInput.send_keys(Keys.ENTER)
def closeUp(self):
try:
self.con.commit()
self.con.close()
self.driver.close()
except Exception as err:
print(err)
def insertDB(self, mNo, mMark, mPrice, mNote, mFile):
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):
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
", "")
mark = mark.replace(",", "")
note = note.replace("爱心东东
", "")
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)
# 取下一页的数据，直到最后一页
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
2)心得体会:本次实验是对老师ppt的复刻,让我熟悉了selenium的流程与使用。
作业②:
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。
输出信息：MYSQL的输出信息如下
| 序号 | 股票代码 | 股票名称 | 最新报价 | 涨跌幅 | 涨跌额 | 成交量 | 成交额 | 振幅 | 最高 | 最低 | 今开 | 昨收 |
| 1 | 688093 | N世华 | 28.47 | 62.22% | 10.92 | 26.13万 | 7.6亿 | 22.34 | 32.0 | 28.08 | 30.2 | 17.55 |
| 2 | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
创建数据库(只是其中之一,其它两个把表名的hs换成sh,sz)
CREATE TABLE hs_stock(
rank VARCHAR(5),
stockCode VARCHAR(10),
stockName VARCHAR(10),
latestPrice VARCHAR(10),
changeRange VARCHAR(10),
changeValue VARCHAR(10),
dealNumber VARCHAR(10),
dealTotal VARCHAR(10),
amplitude VARCHAR(10),
maxPrice VARCHAR(10),
minPrice VARCHAR(10),
today VARCHAR(10),
yesterday VARCHAR(10)
)DEFAULT CHARACTER SET = utf8;
爬取股票
from selenium import webdriver
from time import sleep
import pymysql,threading
def getStock(url,useless):
# 连接数据库,获取游标对象
db = pymysql.connect(host="127.0.0.1",port=3306,user="root",passwd="root",db="crawler",charset="utf8")
cursor = db.cursor()
driver = webdriver.Chrome()
driver.get(url)
# 三个板块的url[-10:-7]分别对应hs,sh,sz,根据url来确定插入哪个表
tableName = url[-10:-7]+"stock"
# 获取总页数,我全都要
page = driver.find_elements_by_xpath("//*[@id="main-table_paginate"]/span[1]//a")[-1].get_attribute("data-index")
for i in range(int(page)):
trList = driver.find_elements_by_css_selector("#table_wrapper-table > tbody > tr")
for tr in trList:
d = tr.text.split()
d = d[0:3]+d[6:16]
# 最近发现把要插入的数据存在list中,只要写一个list名就行,更方便
cursor.execute("insert into "+tableName+" values (%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)",d)
# 点击"下一页",并提交事务
driver.find_element_by_xpath("//*[@id="main-table_paginate"]/a[2]").click()
db.commit()
sleep(3)
url = "http://quote.eastmoney.com/center/gridlist.html#"
stockType=["hs_a_board","sh_a_board","sz_a_board"]
# 使用多线程,加快速度
for stype in stockType:
T = threading.Thread(target=getStock,args=(url+stype,None)) #None只是一个凑数的,只有一个参数的话一直报错
T.start()
图片:
2)心得体会:此网站已经爬取非常多次了,大家也都心知肚明,本次实验收获是插入数据只要将数据存放在列表中,插入写列表名就行,不需要写很多变量;还有就是多线程好像两行就行了,不用像课本写一大堆
作业③:
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
输出信息：MYSQL的输出信息如下
1)代码:
创建数据库
CREATE TABLE course(
Id INT PRIMARY KEY AUTO_INCREMENT,
cCourse VARCHAR(20),
cCollege VARCHAR(20),
cTeam VARCHAR(30),
cCount VARCHAR(10),
cProcess VARCHAR(30),
cBrief VARCHAR(200)
)DEFAULT CHARACTER SET = utf8;
模拟登录
过程还是挺顺利,就是登录操作时,账号send_keys()失效,而密码却没出错,所以没想到是frame的问题。
后面百度了一下,从博客中偷学了一招切换frame,解决了卡了几个小时的问题,蕾姆
from selenium import webdriver
from time import sleep
url = "https://www.icourse163.org"
driver = webdriver.Chrome()
driver.get(url)
sleep(1)
driver.find_element_by_xpath("//*[@id="app"]/div/div/div[1]/div[3]/div[3]/div").click()
sleep(1)
driver.find_element_by_xpath("//div[starts-with(@id,'auto-id')]/div/div/div/div[2]/span").click()
sleep(1)
driver.find_element_by_xpath("//div[starts-with(@id,'auto-id')]/div/div/div/div/div[1]/div/div[1]/div[1]/ul/li[2]").click()
sleep(1)
#
driver.switch_to.frame(driver.find_elements_by_tag_name("iframe")[1])
sleep(1)
driver.find_element_by_xpath("//input[@id='phoneipt']").send_keys("13395068352")
sleep(1)
driver.find_element_by_xpath("//input[@placeholder="请输入密码"]").send_keys("xxx11xxx")
sleep(1)
driver.find_element_by_xpath("//a[@id="submitBtn"]").click()
sleep(3)
爬取课程信息
from selenium import webdriver
from time import sleep
import pymysql
# 后面频繁切换窗口,整合成一个函数
def switchWindow(index):
windows = driver.window_handles
driver.switch_to.window(windows[index])
# 连接数据库
db = pymysql.connect(host="127.0.0.1",port=3306,user="root",passwd="root",db="crawler",charset="utf8")
cursor = db.cursor()
url = "https://www.icourse163.org"
driver = webdriver.Chrome()
driver.get(url)
driver.maximize_window()
driver.find_element_by_xpath('//div[@class="u-baseinputui"]/input[@class="j-textarea inputtxt"]').send_keys("生化")
sleep(1)
driver.find_element_by_xpath('//div[@class="u-search-icon"]/span[@class="u-icon-search2 j-searchBtn"]').click()
sleep(1)
# 获取页面总数,如果只有一页的话,就没有分页的按钮,pageList长度就为0,那么要爬取的页数就为1;否则总页数就是倒二个a标签的text值
pageList = driver.find_elements_by_xpath("//a[@class='th-bk-main-gh']")
page = int(pageList[-2].text) if len(pageList) else 1
for i in range(page):
# 每一页课程的集合
courseList = driver.find_elements_by_xpath('//div[@class="u-clist f-bgw f-cb f-pr j-href ga-click"]')
# 每一页爬取的个数,课程数>3就小爬3页,否则就全爬,意思意思就好
length = min(3,len(courseList))
for course in courseList[:length]:
info = [] # 简化数据库插入操作
# 切换到主窗口
switchWindow(0)
sleep(1)
courseName = course.find_element_by_xpath(".//span[@class=' u-course-name f-thide']").text
info.append(courseName)
college = course.find_element_by_xpath(".//a[@class='t21 f-fc9']").text
info.append(college)
team = course.find_element_by_xpath(".//a[@class='f-fc9']").text
info.append(team)
count = course.find_element_by_xpath(".//span[@class='hot']").text
count = count[:count.index("人")+1]
info.append(count)
# 有的信息只能点进链接才能获取
course.click()
sleep(1)
# 切换到新打开的窗口
switchWindow(-1)
sleep(2)
time = driver.find_element_by_xpath("//div[@class='course-enroll-info_course-info_term-info_term-time']/span[2]").text
brief = driver.find_element_by_xpath("//div[@id='j-rectxt2']").text
driver.close()
info.append(time)
info.append(brief)
cursor.execute("insert into course(cCourse,cCollege,cTeam,cCount,cProcess,cBrief) values (%s,%s,%s,%s,%s,%s)",info)
db.commit()
# 上面最后不是在主窗口,要记得切换回来
switchWindow(0)
if page>1 and i<page-1:# 只有总页数不止一页而且不是最后一页,才点击"下一页"按钮
driver.find_elements_by_xpath("//a[@class='th-bk-main-gh']")[-1].click()
sleep(1)
db.close()
2)心得体会:
刚开始没去调窗口大小,课程点击只能点两个,第三个就报错,浩大将军在我头上点了三下,一生二,二生三,三生万物,暗示我将窗口设为全屏,就能解决了;还有就是得切换窗口,不然会有找不到元素的错误