MOOC Python网络爬虫程序技术-深圳信息职业技术学院 中国大学慕课答案

MOOCPython网络爬虫程序技术-深圳信息职业技术学院中国大学慕课答案测验1、问题：importflaskapp=flask.Flask(__name__)@app.route(/)defindex():try:fobj=open(index.htm,rb)data=fobj.read()fobj.close()returndataexceptExceptionaserr:returnstr(err)if__name__==__main__:app.run()index.htm文件h1WelcomePythonFlaskWeb/h1ItisveryeasytomakeawebsitebyPythonFlask.那么访问:5000可以看到index.htm的结果？选项：A、正确B、错误正确答案:【正确】GETPOST1、问题：服务器程序可以接受get与post的提交信息importꢀflaskapp=flask.Flask(__name__)@app.route(/,____________________)defꢀindex():ꢀꢀꢀꢀtry:ꢀꢀꢀꢀꢀꢀꢀꢀprovince=flask.request.values.get(province)ꢀifꢀprovinceꢀinꢀflask.request.valuesꢀelseꢀꢀꢀꢀꢀꢀꢀꢀꢀcityꢀ=ꢀflask.request.values.get(city)ꢀifꢀcityꢀinꢀflask.request.valuesꢀelseꢀꢀꢀꢀꢀꢀꢀꢀꢀnoteꢀ=ꢀflask.request.values.get(note)ꢀifꢀnoteꢀinꢀflask.request.valuesꢀelseꢀꢀꢀꢀꢀꢀꢀꢀꢀreturnꢀprovince+,+city+\n+noteꢀꢀꢀꢀexceptꢀExceptionꢀasꢀerr:ꢀꢀꢀꢀꢀꢀꢀꢀreturnꢀstr(err)ifꢀ__name__==__main__:ꢀꢀꢀꢀapp.run()缺失的语句是选项：A、methods=[GET，POST]B、method=[GET，POST]C、methods=[POST]D、method=[POST]正确答案:【methods=[GET，POST]】POST1、问题：编程客户端client.py程序如下：importꢀurllib.parseimportꢀurllib.requesturl=:5000try:ꢀꢀꢀꢀprovince=ꢀurllib.parse.quote(广东)ꢀꢀꢀꢀcity=ꢀurllib.parse.quote(深圳)ꢀꢀꢀꢀdata=province=+province+city=+cityꢀꢀꢀꢀ___________________________ꢀꢀꢀꢀ____________________________ꢀꢀꢀꢀhtmlꢀ=ꢀhtml.read()ꢀꢀꢀꢀhtmlꢀ=ꢀhtml.decode()ꢀꢀꢀꢀprint(html)exceptꢀExceptionꢀasꢀerr:ꢀꢀꢀꢀprint(err)服务器server.py程序importꢀflaskapp=flask.Flask(__name__)@app.route(/,methods=[POST])defꢀindex():ꢀꢀꢀꢀtry:ꢀꢀꢀꢀꢀꢀꢀꢀprovince=flask.request.form.get(province)ꢀifꢀprovinceꢀinꢀflask.request.formꢀelseꢀꢀꢀꢀꢀꢀꢀꢀꢀcityꢀ=ꢀflask.request.form.get(city)ꢀifꢀcityꢀinꢀflask.request.formꢀelseꢀꢀꢀꢀꢀꢀꢀꢀꢀreturnꢀprovince+,+cityꢀꢀꢀꢀexceptꢀExceptionꢀasꢀerr:ꢀꢀꢀꢀꢀꢀꢀꢀreturnꢀstr(err)ifꢀ__name__==__main__:ꢀꢀꢀꢀapp.run()缺失的语句是选项：A、data=data.decode()；html=urllib.request.urlopen(:5000，data=data)B、data=data.encode()；html=urllib.request.urlopen(:5000，data=data)C、data=data.encode()；html=urllib.request.urlopen(:5000?data=+data)D、data=data.decode()；html=urllib.request.urlopen(:5000?data=+data)正确答案:【data=data.encode()；html=urllib.request.urlopen(:5000，data=data)】下载文件1、问题：服务器程序可以下载文件图像.jpgimportꢀflaskimportꢀosapp=flask.Flask(__name__)@app.route(/)defꢀindex():ꢀꢀꢀꢀifꢀfileNameꢀnotꢀinꢀflask.request.values:ꢀꢀꢀꢀꢀꢀꢀꢀreturnꢀ图像.jpgꢀꢀꢀꢀelse:ꢀꢀꢀꢀꢀꢀꢀꢀdataꢀ=ꢀbꢀꢀꢀꢀꢀꢀꢀꢀtry:ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀ_____________________________________________ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀifꢀfileNameꢀ!=ꢀꢀandꢀos.path.exists(fileName):ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀfobjꢀ=ꢀopen(fileName,ꢀrb)ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀ_________________________ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀfobj.close()ꢀꢀꢀꢀꢀꢀꢀꢀexceptꢀExceptionꢀasꢀerr:ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀdataꢀ=ꢀstr(err).encode()ꢀꢀꢀꢀꢀꢀꢀꢀreturnꢀdataifꢀ__name__==__main__:ꢀꢀꢀꢀapp.run()缺失的语句是选项：A、fileName=flask.request.values.get(fileName)；data=fobj.read()B、fileName=flask.request.args.get(fileName)；data=fobj.read()C、fileName=flask.request.form.get(fileName)；data=fobj.read()D、都不对正确答案:【fileName=flask.request.values.get(fileName)；data=fobj.read()】上传文件1、问题：服务器程序接受客户端上传的文件名称fileName，然后获取文件数据保存importꢀflaskapp=flask.Flask(__name__)@app.route(/upload,methods=[POST])defꢀuploadFile():ꢀꢀꢀꢀmsg=ꢀꢀꢀꢀtry:ꢀꢀꢀꢀꢀꢀꢀꢀifꢀfileNameꢀinꢀflask.request.values:ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀfileNameꢀ=ꢀflask.request.values.get(fileName)ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀ__________________________________ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀfobj=open(uploadꢀ+fileName,wb)ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀfobj.write(data)ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀfobj.close()ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀmsg=OKꢀꢀꢀꢀꢀꢀꢀꢀelse:ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀmsg=没有按要求上传文件ꢀꢀꢀꢀexceptꢀExceptionꢀasꢀerr:ꢀꢀꢀꢀꢀꢀꢀꢀprint(err)ꢀꢀꢀꢀꢀꢀꢀꢀmsg=str(err)ꢀꢀꢀꢀreturnꢀmsgifꢀ__name__==__main__:ꢀꢀꢀꢀapp.run()缺失的语句是选项：A、data=flask.request.read()B、data=flask.request.get_data()C、data=flask.request.values.read()D、data=flask.request.values.get_data()正确答案:【data=flask.request.get_data()】数据库1、问题：classꢀStudentDB:ꢀꢀꢀꢀdefꢀopenDB(self):ꢀꢀꢀꢀꢀꢀꢀꢀself.con=sqlite3.connect(students.db)ꢀꢀꢀꢀꢀꢀꢀꢀself.cursor=self.con.cursor()ꢀꢀꢀꢀdefꢀcloseDB(self):ꢀꢀꢀꢀꢀꢀꢀꢀmit()ꢀꢀꢀꢀꢀꢀꢀꢀself.con.close()ꢀꢀꢀꢀdefꢀinitTable(self):ꢀꢀꢀꢀꢀꢀꢀꢀres={}ꢀꢀꢀꢀꢀꢀꢀꢀtry:ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀself.cursor.execute(createꢀtableꢀstudentsꢀ(Noꢀvarchar(16)ꢀprimaryꢀkey,Nameꢀvarchar(16),ꢀSexꢀvarchar(8),ꢀAgeꢀint))ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀres[msg]=OKꢀꢀꢀꢀꢀꢀꢀꢀexceptꢀExceptionꢀasꢀerr:ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀres[msg]=str(err)ꢀꢀꢀꢀꢀꢀꢀꢀreturnꢀresꢀꢀꢀꢀdefꢀinsertRow(self,No,Name,Sex,Age):ꢀꢀꢀꢀꢀꢀꢀꢀres={}ꢀꢀꢀꢀꢀꢀꢀꢀtry:ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀ___________________________________________ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀres[msg]=OKꢀꢀꢀꢀꢀꢀꢀꢀexceptꢀExceptionꢀasꢀerr:ꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀꢀres[msg]=str(err)ꢀꢀꢀꢀꢀꢀꢀꢀreturnꢀres程序插入一条学生记录，缺失的语句是选项：A、self.cursor.execute(insertintostudents(No，Name，Sex，Age)values(%s，%s，%s，%s)，(No，Name，Sex，Age))B、self.cursor.execute(insertintostudents(No，Name，Sex，Age)values(%s，%s，%s，%d)，(No，Name，Sex，Age))C、self.cursor.execute(insertintostudents(No，Name，Sex，Age)values(@No，@Name，@Sex，@Age)，(No，Name，Sex，Age))D、self.cursor.execute(insertintostudents(No，Name，Sex，Age)values(?，?，?，?)，(No，Name，Sex，Age))正确答案:【self.cursor.execute(insertintostudents(No，Name，Sex，Age)values(?，?，?，?)，(No，Name，Sex，Age))】测验1、问题：importꢀres=testingꢀsearchreg=r[A-Za-z]+\bm=re.search(reg,s)whileꢀm!=None:ꢀꢀꢀꢀstart=m.start()ꢀꢀꢀꢀend=m.end()ꢀꢀꢀꢀprint(s[start:end],end=ꢀ)ꢀꢀꢀꢀs=s[end:]ꢀꢀꢀꢀm=re.search(reg,s)结果：选项：A、testingB、testingsearchC、searchD、searchtesting正确答案:【testingsearch】测验11、问题：importflaskapp=flask.Flask(web)@app.route(/,___________)defindex():#......returnhelloapp.run()程序要求能接收POST数据，缺失的语句是选项：A、methods=[GET]B、methods=[POST]C、method=[GET]D、method=[POST]正确答案:【methods=[POST]】2、问题：importres="abbcabab"——————————————print(re.search(reg,s))查找到"abab"，缺失的语句是选项：A、reg=r(ab)+B、reg=r(ab)+$C、reg=rab+$D、reg=rab+正确答案:【reg=r(ab)+$】3、问题：importurllib.requestresp=urllib.request.urlopen(:5000)______________print(html)获取网站的HTML文本数据，缺少的语句是：选项：A、html=resp.read.decode()B、html=resp.read().decode()C、html=resp.read.encode()D、html=resp.read().encode()正确答案:【html=resp.read().decode()】4、问题：importꢀres=searchingꢀsearch_______________print(re.search(reg,s))查找s中的第一个search字符串，缺失的语句是选项：A、reg=r[a-zA-Z]+B、reg=r[a-zA-Z]+$C、reg=r^[a-zA-Z]+$D、reg=r$[a-zA-Z]+^正确答案:【reg=r[a-zA-Z]+】5、问题：importꢀres=searchingꢀsearch_______________print(re.search(reg,s))查找s中的最后一个search单词，缺失的语句是选项：A、reg=r[A-Za-z]+$B、reg=r^[A-Za-z]+$C、reg=r^[A-Za-z]+D、reg=r[A-Za-z]+正确答案:【reg=r[A-Za-z]+$】6、问题：importrereg=rx[^ab0-9]ym=re.search(reg,xayx2yxcy)print(m)结果匹配xcy:_sre.SRE_Matchobject;span=(6,9),match='xcy'选项：A、正确B、错误正确答案:【正确】7、问题：importrereg=rx[0-9]ym=re.search(reg,xyx2y)print(m)结果匹配x2y:_sre.SRE_Matchobject;span=(0,2),match='xy'选项：A、正确B、错误正确答案:【错误】8、问题：importrereg=rcar\bm=re.search(reg,Thecarisblack)print(m)结果匹配car，因为car后面是以个空格：_sre.SRE_Matchobject;span=(4,7),match='car'选项：A、正确B、错误正确答案:【正确】9、问题：importrereg=ra\nb?m=re.search(reg,ca\nbcabc)print(m)结果匹配a\n\b:_sre.SRE_Matchobject;span=(1,4),match='ab'选项：A、正确B、错误正确答案:【错误】10、问题：importres=xaabababym=re.search(rab|ba,s)print(m)结果匹配ab或者ba都可以：_sre.SRE_Matchobject;span=(2,4),match='ba'选项：A、正确B、错误正确答案:【错误】BeautifulSoup1、问题：frombs4importBeautifulSoupdoc='''htmlheadtitleTheDormouse'sstory/title/headbodypclass=titlebTheDormouse'sstory/b/ppclass=storyOnceuponatimetherewerethreelittlesisters;andtheirnameswereahref=/elsieclass=sisterid=link1Elsie/a,ahref=/lacieclass=sisterid=link2Lacie/aandahref=/tillieclass=sisterid=link3Tillie/a;andtheylivedatthebottomofawell./ppclass=story.../p/body/html'''soup=BeautifulSoup(doc,lxml)_______________________________print(tag)程序结果找到class=story的p元素,缺失的语句是选项：A、tag=soup.find(p,attrs={class:story})B、tag=soup.find(p,attr={class:story})C、tag=soup.find(p)D、tag=soup.find(p,class=story)正确答案:【tag=soup.find(p,attrs={class:story})】BeautifulSoup1、问题：frombs4importBeautifulSoupdoc='''htmlheadtitleTheDormouse'sstory/title/headbodypclass=titlebTheDormouse'sstory/b/ppclass=storyOnceuponatimetherewerethreelittlesisters;andtheirnameswereahref=/elsieclass=sisterid=link1Elsie/a,ahref=/lacieclass=sisterid=link2Lacie/aandahref=/tillieclass=sisterid=link3Tillie/a;andtheylivedatthebottomofawell./ppclass=story.../p/body/html'''soup=BeautifulSoup(doc,lxml)___________________________________fortagintags:print(tag)查找文档中class=sister的元素,缺失语句是：选项：A、tags=soup.find(name=None,attrs={class:sister})B、tags=soup.find(attrs={class:sister})C、tags=soup.find_all(attrs={class:sister})D、tags=soup.find_all(name=None,attrs={class:sister})正确答案:【tags=soup.find_all(name=None,attrs={class:sister})】查找1、问题：frombs4importBeautifulSoupdoc='''htmlheadtitleTheDormouse'sstory/title/headbodypclass=titlebTheDormouse'sstory/b/ppclass=storyOnceuponatimetherewerethreelittlesisters;andtheirnameswereahref=/elsieclass=sisterid=link1Elsie/a,ahref=/lacieclass=sisterid=link2Lacie/aandahref=/tillieclass=sisterid=link3Tillie/a;andtheylivedatthebottomofawell./ppclass=story.../p/body/html'''soup=BeautifulSoup(doc,lxml)______________________________________fortagintags:print(tag[href])结果是：/elsie/lacie/tillie缺失的语句是：选项：A、tags=soup.select(pa)B、tags=soup.select(p[]a)C、tags=soup.select(p[class]a)D、tags=soup.select(p[class='story']a)正确答案:【tags=soup.select(p[class='story']a)】测验21、问题：查找文档中所有p超级链接包含的文本值frombs4importBeautifulSoupdoc='''htmlheadtitleTheDormouse'sstory/title/headbodypclass=titlebTheDormouse'sstory/b/ppclass=storyOnceuponatimetherewerethreelittlesisters;andtheirnameswereahref=/elsieclass=sisterid=link1Elsie/a,ahref=/lacieclass=sisterid=link2Lacie/aandahref=/tillieclass=sisterid=link3Tillie/a;andtheylivedatthebottomofawell./ppclass=story.../p/body/html'''soup=BeautifulSoup(doc,lxml)__________________________________fortagintags:________________________缺失的语句是：选项：A、tags=soup.find(p);print(tag.text)B、tags=soup.find(p);print(tag[text])C、tags=soup.find_all(p);print(tag.text)D、tags=soup.find_all(p);print(tag[text])正确答案:【tags=soup.find_all(p);print(tag.text)】2、问题：找出文档中pclass=titlebTheDormouse'sstory/b/p的b元素节点的所有父节点的名称。frombs4importBeautifulSoupdoc='''htmlheadtitleTheDormouse'sstory/title/headbodypclass=titlebTheDormouse'sstory/b/ppclass=storyOnceuponatimetherewerethreelittlesisters;andtheirnameswereahref=/elsieclass=sisterid=link1Elsie/a,ahref=/lacieclass=sisterid=link2Lacie/aandahref=/tillieclass=sisterid=link3Tillie/a;andtheylivedatthebottomofawell./ppclass=story.../p/body/html'''soup=BeautifulSoup(doc,lxml)print()________________________________whiletag:print()____________________________缺失的语句是：选项：A、tag=soup.find(b);tag=tag.parentB、tag=soup.find(b);tag=tag[parent]C、tag=soup.find_all(b);tag=tag.parentD、tag=soup.find_all(b);tag=tag[parent]正确答案:【tag=soup.find(b);tag=tag.parent】3、问题：获取p元素的所有直接子元素节点frombs4importBeautifulSoupdoc='''htmlheadtitleTheDormouse'sstory/title/headbodypclass=titlebTheiDormouse's/istory/bOnceuponatime.../p/body/html'''soup=BeautifulSoup(doc,lxml)________________forxin__________________:print(x)缺失的语句是：选项：A、tag=soup.find(p);tag.childrenB、tag=soup.find(p);tag.childC、tag=soup.find_all(p);tag.childrenD、tag=soup.find_all(p);tag.child正确答案:【tag=soup.find(p);tag.children】4、问题：获取p元素的所有子孙元素节点frombs4importBeautifulSoupdoc='''htmlheadtitleTheDormouse'sstory/title/headbodypclass=titlebTheiDormouse's/istory/bOnceuponatime.../p/body/html'''soup=BeautifulSoup(doc,lxml)______________________________forxin________________________:print(x)缺失的语句是：选项：A、tag=soup.find(p);tag.childrenB、tag=soup.find(p);tag.descendantsC、tag=soup.find_all(p);tag.childrenD、tag=soup.find_all(p);tag.descendants正确答案:【tag=soup.find(p);tag.descendants】5、问题：soup.select(a)查找文档中所有a元素节点；选项：A、正确B、错误正确答案:【正确】6、问题：soup.select(pa)查找文档中所有p节点下的所有a元素节点；选项：A、正确B、错误正确答案:【正确】7、问题：soup.select(p[class='story']a)查找文档中所有属性class=story的p节点下的所有a元素节点；选项：A、正确B、错误正确答案:【正确】8、问题：soup.select(p[class]a)查找文档中所有具有class属性的p节点下的所有a元素节点；选项：A、正确B、错误正确答案:【正确】9、问题：soup.select(a[id='link1'])查找属性id=link1的a节点；选项：A、正确B、错误正确答案:【正确】10、问题：soup.select(bodyheadtitle)查找body下面head下面的title节点；选项：A、正确B、错误正确答案:【正确】递归1、问题：(1)books.htmh3计算机/h3ulliahref=database.htm数据库/a/liliahref=program.htm程序设计/a/liliahref=network.htm计算机网络/a/li/ul(2)database.htmh3数据库/h3ulliahref=mysql.htmMySQL数据库/a/li/ul(3)program.htmh3程序设计/h3ulliahref=python.htmPython程序设计/a/liliahref=java.htmJava程序设计/a/li/ul(4)network.htmh3计算机网络/h3(5)mysql.htmh3MySQL数据库/h3(6)python.htmh3Python程序设计/h3(7)java.htmh3Java程序设计/h3frombs4importBeautifulSoupimporturllib.requestdefspider(url):try:data=urllib.request.urlopen(url)data=data.read()data=data.decode()soup=BeautifulSoup(data,lxml)print(soup.find(h3).text)____________________________________forlinkinlinks:href=link[href]___________________________________spider(url)exceptExceptionaserr:print(err)start_url=:5000spider(start_url)print(TheEnd)递归调用选项：A、links=soup.select(a);url=start_url+hrefB、links=soup.select(li);url=start_url+/+hrefC、links=soup.select(a);url=start_url+/+hrefD、links=soup.select(li);url=start_url+href正确答案:【links=soup.select(a);url=start_url+/+href】测试1、问题：frombs4importBeautifulSoupimporturllib.requestclassStack:def__init__(self):self.st=[]defpop(self):returnself.st.pop()defpush(self,obj):self.st.append(obj)defempty(self):returnlen(self.st)==0defspider(url):stack=Stack()stack.push(url)whilenotstack.empty():url=stack.pop()try:data=urllib.request.urlopen(url)data=data.read()data=data.decode()soup=BeautifulSoup(data,lxml)print(soup.find(h3).text)links=soup.select(a)foriin_______________________________:href=links[i][href]url=start_url+/+hrefstack.push(url)exceptExceptionaserr:print(err)start_url=:5000spider(start_url)print(TheEnd)选项：A、range(len(links)-1,-1,-1)B、range(len(links),-1,-1)C、range(len(links)-1,0,-1)D、range(len(links),0,-1)正确答案:【range(len(links)-1,-1,-1)】测试1、问题：在主线程中启动一个子线程执行reading函数。importthreadingimporttimeimportrandomdefreading():foriinrange(10):print(reading,i)time.sleep(random.randint(1,2))_______________________________r.setDaemon(False)r.start()print(TheEnd)选项：A、r=threading.Thread(reading)B、r=threading.Thread(target=reading())C、r=threading.Thread(target=reading)D、r=Thread(target=reading)正确答案:【r=threading.Thread(target=reading)】测试1、问题：不重复访问网站，使用队列的程序frombs4importBeautifulSoupimporturllib.requestclassQueue:def__init__(self):self.st=[]deffetch(self):returnself.st.pop(0)defenter(self,obj):self.st.append(obj)defempty(self):returnlen(self.st)==0defspider(url):globalurlsqueue=Queue()queue.enter(url)while________________________:url=queue.fetch()ifurlnotinurls:try:urls.append(url)data=urllib.request.urlopen(url)data=data.read()data=data.decode()soup=BeautifulSoup(data,lxml)print(soup.find(h3).text)links=soup.select(a)forlinkinlinks:________________url=start_url+/+hrefqueue.enter(url)exceptExceptionaserr:print(err)start_url=:5000urls=[]spider(start_url)print(TheEnd)选项：A、queue.empty();href=link[href]B、notqueue.empty();href=link[href]C、queue.empty();href=link.hrefD、notqueue.empty();href=link.href正确答案:【notqueue.empty();href=link[href]】测验31、问题：defspider(url):ꢀꢀ#获取新的地址newUrlifnewUrl:spider(newUrl)下面说法正确的是：选项：A、不是递归调用B、一定会出现死循环C、找不到newUrl时会结束递归调用D、找不到newUrl时也不会结束递归调用正确答案:【找不到newUrl时会结束递归调用】2、问题：深度优先爬取说法正确的是选项：A、结果与递归调用爬取一样B、结果与递归调用爬取不一样C、效率比函数递归调用爬取低D、效率比函数递归调用爬取高正确答案:【结果与递归调用爬取一样】3、问题：广度优先爬取数据，说法正确的是：选项：A、爬取数据的顺序与深度优先的不同B、爬取数据的顺序与深度优先的相同C、爬取数据的顺序与函数递归方法相同D、都不对正确答案:【爬取数据的顺序与深度优先的不同】4、问题：有一个dowbload(url)函数下载url图像:importthreadingdefdownload(url):pass用多线程调用它，方法是：选项：A、T=threading.Thread(target=download,args=[url])T.start()B、T=threading.Thread(target=download,args=url)T.start()C、T=threading.Thread(target=download,args=(url))T.start()D、都不对正确答案:【T=threading.Thread(target=download,args=[url])T.start()】5、问题：爬取网站的很多图片时，说法正确是：选项：A、使用单线程效率高，程序简单B、使用单线程效率高，程序复杂C、使用多线程效率高，程序简单D、使用多线程效率高，程序复杂正确答案:【使用多线程效率高，程序复杂】6、问题：url=/weather/101280601.shtmlheaders={User-Agent:Mozilla/5.0(Windows;U;WindowsNT6.0x64;en-US;rv:1.9pre)Gecko/2008072421Minefield/3.0.2pre}req=urllib.request.Request(url,headers=headers)data=urllib.request.urlopen(req)data=data.read()其中headers的作用是为了模拟浏览器选项：A、正确B、错误正确答案:【正确】7、问题：soup.select(body[class]a)查找body下面所有具有class属性的节点下面的a节点；选项：A、正确B、错误正确答案:【正确】8、问题：soup.select(body[class])查找body下面所有具有class属性的节点；选项：A、正确B、错误正确答案:【正确】9、问题：soup.select(bodyheadtitle)查找body下面head下面的title节点；选项：A、正确B、错误正确答案:【正确】10、问题：soup.select(a[id='link1'])查找属性id=link1的a节点；选项：A、正确B、错误正确答案:【正确】测试1、问题：importscrapyclassMySpider(scrapy.Spider):name=mySpiderdefstart_requests(self):url=':5000'_________________________________________defparse(self,response):print(response.url)data=response.body.decode()print(data)选项：A、yieldscrapy.Request(url=url,callback=self.parse)B、yieldscrapy.Request(url=url,callback=parse)C、returnscrapy.Request(url=url,callback=self.parse)D、returnscrapy.Request(url=url,callback=parse)正确答案:【yieldscrapy.Request(url=url,callback=self.parse)】测验1、问题：fromscrapy.selectorimportSelectorhtmlText='''htmlbodybookstorebooktitlelang=engHarryPotter/titleprice29.99/price/bookbooktitlelang=engLearningXML/titleprice39.95/price/book/bookstore/body/html'''selector=Selector(text=htmlText)print(type(selector));print(selector)_______________print(type(s))print(s)查找所有的title选项：A、s=selector.xpath(title)B、s=selector.xpath(//title)C、s=selector.xpath(/title)D、s=selector.xpath(///title)正确答案:【s=selector.xpath(//title)】测验1、问题：fromscrapy.selectorimportSelectorhtmlText='''htmlbodybookstoretitlebooks/titlebooktitleNovel/titletitlelang=engHarryPotter/titleprice29.99/price/bookbooktitleTextBook/titletitlelang=engLearningXML/titleprice39.95/price/book/bookstore/body/html'''selector=Selector(text=htmlText)_____________________________________foreins:print(e)程序结果：Selectorxpath='//book/title'data='titleNovel/title'Selectorxpath='//book/title'data='titlelang=engHarryPotter/title'Selectorxpath='//book/title'data='titleTextBook/title'Selectorxpath='//book/title'data='titlelang=engLearningXML/title'选项：A、s=selector.xpath(/book).xpath(./title)B、s=selector.xpath(//book).xpath(./title)C、s=selector.xpath(//book).xpath(/title)D、s=selector.xpath(/book).xpath(/title)正确答案:【s=selector.xpath(//book).xpath(./title)】测验1、问题：fromscrapy.selectorimportSelectorhtmlText='''htmlbodybookstorebookid=b1titlelang=englishHarryPotter/titleprice29.99/price/bookbookid=b2titlelang=chinese学习XML/titleprice39.95/price/book/bookstore/body/html'''selector=Selector(text=htmlText)____________________________________________________print(s.extract_first())s=selector.xpath(//book[@id='b1']/title)print(s.extract_first())程序结果：学习XMLtitlelang=englishHarryPotter/title选项：A、s=selector.xpath(//book/title[@lang='chinese']/text)B、s=selector.xpath(//book/title[lang='chinese']/text)C、s=selector.xpath(//book/title[@lang='chinese']/text())D、s=selector.xpath(//book/title[@lang='chinese']/text)正确答案:【s=selector.xpath(//book/title[@lang='chinese']/text())】测试1、问题：fromscrapy.selectorimportSelectorhtmlText='''htmlbodybookstorebookid=b1titlelang=englishHarryPotter/titleprice29.99/price/bookbookid=b2titlelang=chinese学习XML/titleprice39.95/price/book/bookstore/body/html'''selector=Selector(text=htmlText)____________________________________print(s.extract_first())____________________________________print(s.extract_first())程序结果：titlelang=englishHarryPotter/titletitlelang=chinese学习XML/title选项：A、s=selector.xpath(//book[position=1]/title);s=selector.xpath(//book[position=2]/title)B、s=selector.xpath(//book[position()=2]/title);s=selector.xpath(//book[position()=1]/title)C、s=selector.xpath(//book[position=2]/title);s=selector.xpath(//book[position=1]/title)D、s=selector.xpath(//book[position()=1]/title);s=selector.xpath(//book[position()=2]/title)正确答案:【s=selector.xpath(//book[position()=1]/title);s=selector.xpath(//book[position()=2]/title)】测验41、问题：selector.xpath(//bookstore/book)搜索bookstore下一级的book元素，找到2个；选项：A、正确B、错误正确答案:【正确】2、问题：selector.xpath(//body/book)搜索body下一级的book元素，结果为空；选项：A、正确B、错误正确答案:【正确】3、问题：selector.xpath(//body//book)搜索body下book元素，找到2个；选项：A、正确B、错误正确答案:【正确】4、问题：selector.xpath(/body//book)搜索文档下一级的body下的book元素，找结果为空，因为文档的下一级是html元素，不是body元素；选项：A、正确B、错误正确答案:【正确】5、问题：selector.xpath(/html/body//book)或者selector.xpath(/html//book)搜索book元素，找到2个；选项：A、正确B、错误正确答案:【正确】6、问题：selector.xpah(//book/title)搜索文档中所有book下一级的title元素，找到2个，结果与selector.xpah(//title)、selector.xpath(//bookstore//title)一样；选项：A、正确B、错误正确答案:【正确】7、问题：selector.xpath(//book//price)与selector.xpath(//price)结果一样，都是找到2个price元素；选项：A、正确B、错误正确答案:【正确】8、问题：selector.xpath(/book//price)与selector.xpath(//price)结果一样；选项：A、正确B、错误正确答案:【错误】9、问题：selector.xpath(//book[id='book1']//price)与selector.xpath(//price)结果一样；选项：A、正确B、错误正确答案:【错误】10、问题：selector.xpath(//price/text()).extract()返回price下面的文本字符串选项：A、正确B、错误正确答案:【错误】课程考试1、问题：importflask____________@app.route(/)defindex():returnhelloapp.run()选项：A、app=flask.Flask(web)B、app=flask(web)C、app=Flask(web)D、app=flask.Flask()正确答案:【app=flask.Flask(web)】2、问题：importres=abbcabab——————————————print(re.