這篇文章主要為大家詳細(xì)介紹了簡(jiǎn)單的python爬蟲代碼,文中示例代碼介紹的非常詳細(xì),具有一定的參考價(jià)值,感興趣的小伙伴們可以參考一下。
創(chuàng)新互聯(lián)成立與2013年,是專業(yè)互聯(lián)網(wǎng)技術(shù)服務(wù)公司,擁有項(xiàng)目網(wǎng)站建設(shè)、成都網(wǎng)站制作網(wǎng)站策劃,項(xiàng)目實(shí)施與項(xiàng)目整合能力。我們以讓每一個(gè)夢(mèng)想脫穎而出為使命,1280元高唐做網(wǎng)站,已為上家服務(wù),為高唐各地企業(yè)和個(gè)人服務(wù),聯(lián)系電話:18982081108
python爬蟲代碼示例分享
一、爬取故事段子:
注:部分代碼無法正常運(yùn)行,但仍有一定的參考價(jià)值。
#encoding=utf-8 import urllib2 import re class neihanba(): def spider(self): ''' 爬蟲的主調(diào)度器 ''' isflow=True#判斷是否進(jìn)行下一頁 page=1 while isflow: url="http://www.neihanpa.com/article/list_5_"+str(page)+".html" html=self.load(url) self.deal(html,page) panduan=raw_input("是否繼續(xù)(y/n)!") if panduan=="y": isflow=True page+=1 else: isflow=False def load(self,url): ''' 針對(duì)url地址進(jìn)行全部爬去 :param url: url地址 :return: 返回爬去的內(nèi)容 ''' header = { "User-Agent": " Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36" } request = urllib2.Request(url, headers=header) response = urllib2.urlopen(request) html = response.read() return html def deal(self,html,page): ''' 對(duì)之前爬去的內(nèi)容進(jìn)行正則匹配,匹配出標(biāo)題和正文內(nèi)容 :param html:之前爬去的內(nèi)容 :param page: 正在爬去的頁碼 ''' parrten=re.compile('<li class="piclist\d+">(.*?)</li>',re.S) titleList=parrten.findall(html) for title in titleList: parrten1=re.compile('<a href="/article/\d+.html" rel="external nofollow" >(.*)</a>') ti1=parrten1.findall(title) parrten2=re.compile('<div class="f18 mb20">(.*?)</div>',re.S) til2=parrten2.findall(title) for t in ti1: tr=t.replace("<b>","").replace("</b>","") self.writeData(tr,page) for t in til2: tr=t.replace("<p>","").replace("</p>","").replace("<br>","").replace("<br />","").replace("&ldquo","\"").replace("&rdquo","\"") self.writeData(tr,page) def writeData(self,context,page): ''' 將最終爬去的內(nèi)容寫入文件中 :param context: 匹配好的內(nèi)容 :param page: 當(dāng)前爬去的頁碼數(shù) ''' fileName = "di" + str(page) + "yehtml.txt" with open(fileName, "a") as file: file.writelines(context + "\n") if __name__ == '__main__': n=neihanba() n.spider()
二、爬取智聯(lián):
#encoding=utf-8 import urllib import urllib2 import re class zhiLian(): def spider(self,position,workPlace): ''' 爬蟲的主調(diào)度器 :param position: 職位 :param workPlace: 工作地點(diǎn) ''' url="http://sou.zhaopin.com/jobs/searchresult.ashx?" url+=urllib.urlencode({"jl":workPlace}) url+="&" url+=urllib.urlencode({"kw":position}) isflow=True#是否進(jìn)行下一頁的爬去 page=1 while isflow: url+="&"+str(page) html=self.load(url) self.deal1(html,page) panduan = raw_input("是否繼續(xù)爬蟲下一頁(y/n)!") if panduan == "y": isflow = True page += 1 else: isflow = False def load(self,url): ''' 針對(duì)url地址進(jìn)行全部爬去 :param url: url地址 :return: 返回爬去的內(nèi)容 ''' header = { "User-Agent": " Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36" } request = urllib2.Request(url, headers=header) response = urllib2.urlopen(request) html = response.read() return html def deal1(self,html,page): ''' 對(duì)之前爬去的內(nèi)容進(jìn)行正則匹配,匹配職位所對(duì)應(yīng)的鏈接 :param html:之前爬去的內(nèi)容 :param page: 正在爬去的頁碼 ''' parrten=re.compile('<a\s+style="font-weight:\s+bold"\s+par="ssidkey=y&ss=\d+&ff=\d+&sg=\w+&so=\d+"\s+href="(.*?)" rel="external nofollow" target="_blank">.*?</a>',re.S) til=parrten.findall(html)#爬去鏈接 for t in til: self.deal2(t,page) def deal2(self,t,page): ''' 進(jìn)行二次爬蟲,然后在新的頁面中對(duì)公司、薪資、工作經(jīng)驗(yàn)進(jìn)行匹配 :param t: url地址 :param page: 當(dāng)前匹配的頁數(shù) ''' html=self.load(t)#返回二次爬蟲的內(nèi)容 parrten1=re.compile('<a\s+onclick=".*?"\s+href=".*?" rel="external nofollow" \s+target="_blank">(.*?)\s+.*?<img\s+class=".*?"\s+src=".*?"\s+border="\d+"\s+vinfo=".*?"></a>',re.S) parrten2=re.compile('<li><span>職位月薪:</span><strong>(.*?) <a.*?>.*?</a></strong></li>',re.S) parrent3=re.compile('<li><span>工作經(jīng)驗(yàn):</span><strong>(.*?)</strong></li>',re.S) til1=parrten1.findall(html) til2=parrten2.findall(html) til3=parrent3.findall(html) str="" for t in til1: t=t.replace('<img title="專屬頁面" src="//img03.zhaopin.cn/2012/img/jobs/icon.png" border="0" />',"") str+=t str+="\t" for t in til2: str+=t str += "\t" for t in til3: str+=t self.writeData(str,page) def writeData(self,context,page): ''' 將最終爬去的內(nèi)容寫入文件中 :param context: 匹配好的內(nèi)容 :param page: 當(dāng)前爬去的頁碼數(shù) ''' fileName = "di" + str(page) + "yehtml.txt" with open(fileName, "a") as file: file.writelines(context + "\n") if __name__ == '__main__': position=raw_input("請(qǐng)輸入職位:") workPlace=raw_input("請(qǐng)輸入工作地點(diǎn):") z=zhiLian() z.spider(position,workPlace)
三、爬取貼吧:
#encoding=utf-8 import urllib import urllib2 import re class teiba(): def spider(self,name,startPage,endPage): url="http://tieba.baidu.com/f?ie=utf-8&" url+=urllib.urlencode({"kw":name}) for page in range(startPage,endPage+1): pn=50*(page-1) urlFull=url+"&"+urllib.urlencode({"pn":pn}) html=self.loadPage(url) self.dealPage(html,page) def loadPage(self,url): header={ "User-Agent":" Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.79 Safari/537.36" } request=urllib2.Request(url,headers=header) response=urllib2.urlopen(request) html=response.read() return html def dealPage(self,html,page): partten=re.compile(r'<a\s+rel="noreferrer"\s+href="/p/\d+" rel="external nofollow" \s+title=".*?"\s+target="_blank" class="j_th_tit\s+">(.*?)</a>',re.S) titleList=partten.findall(html) rstr=r'<span\s+class="topic-tag"\s+data-name=".*?">#(.*?)#</span>' for title in titleList: title=re.sub(rstr,"",title) self.writePage(title,page) def writePage(self,context,page): fileName="di"+str(page)+"yehtml.txt" with open(fileName,"a") as file: file.writelines(context+"\n") if __name__ == '__main__': name=raw_input("請(qǐng)輸入貼吧名:") startPage=raw_input("請(qǐng)輸入起始頁:") endPage=raw_input("請(qǐng)輸入終止頁:") t=teiba() t.spider(name,int(startPage),int(endPage))
以上就是簡(jiǎn)單的python爬蟲代碼的詳細(xì)內(nèi)容了,看完之后是否有所收獲呢?如果想了解更多相關(guān)內(nèi)容,歡迎來創(chuàng)新互聯(lián)行業(yè)資訊!
新聞名稱:舉例說明簡(jiǎn)單的python爬蟲代碼
文章地址:http://jinyejixie.com/article4/jdogie.html
成都網(wǎng)站建設(shè)公司_創(chuàng)新互聯(lián),為您提供云服務(wù)器、企業(yè)網(wǎng)站制作、品牌網(wǎng)站設(shè)計(jì)、標(biāo)簽優(yōu)化、面包屑導(dǎo)航、App開發(fā)
聲明:本網(wǎng)站發(fā)布的內(nèi)容(圖片、視頻和文字)以用戶投稿、用戶轉(zhuǎn)載內(nèi)容為主,如果涉及侵權(quán)請(qǐng)盡快告知,我們將會(huì)在第一時(shí)間刪除。文章觀點(diǎn)不代表本網(wǎng)站立場(chǎng),如需處理請(qǐng)聯(lián)系客服。電話:028-86922220;郵箱:631063699@qq.com。內(nèi)容未經(jīng)允許不得轉(zhuǎn)載,或轉(zhuǎn)載時(shí)需注明來源: 創(chuàng)新互聯(lián)