Py爬蟲項目
阿新 • • 發佈：2018-06-17
sflow like quest html += ted AD mozilla ash
爬取內涵段子：
#encoding=utf-8 import urllib2 import re class neihanba(): def spider(self): ‘‘‘ 爬蟲的主調度器 ‘‘‘ isflow=True#判斷是否進行下一頁 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(y/n)!") if panduan=="y": isflow=True page+=1 else: isflow=False def load(self,url): ‘‘‘ 針對url地址進行全部爬去 :param url: url地址 :return: 返回爬去的內容‘‘‘ 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): ‘‘‘ 對之前爬去的內容進行正則匹配，匹配出標題和正文內容 :param html:之前爬去的內容 :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">(.*)</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): ‘‘‘ 將最終爬去的內容寫入文件中 :param context: 匹配好的內容 :param page: 當前爬去的頁碼數 ‘‘‘ fileName = "di" + str(page) + "yehtml.txt" with open(fileName, "a") as file: file.writelines(context + "\n") if __name__ == ‘__main__‘: n=neihanba() n.spider()
爬取智聯：
#encoding=utf-8 import urllib import urllib2 import re class zhiLian(): def spider(self,position,workPlace): ‘‘‘ 爬蟲的主調度器 :param position: 職位 :param workPlace: 工作地點 ‘‘‘ url="http://sou.zhaopin.com/jobs/searchresult.ashx?" url+=urllib.urlencode({"jl":workPlace}) url+="&" url+=urllib.urlencode({"kw":position}) isflow=True#是否進行下一頁的爬去 page=1 while isflow: url+="&"+str(page) html=self.load(url) self.deal1(html,page) panduan = raw_input("是否繼續爬蟲下一頁(y/n)!") if panduan == "y": isflow = True page += 1 else: isflow = False def load(self,url): ‘‘‘ 針對url地址進行全部爬去 :param url: url地址 :return: 返回爬去的內容 ‘‘‘ 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): ‘‘‘ 對之前爬去的內容進行正則匹配，匹配職位所對應的鏈接 :param html:之前爬去的內容 :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="(.*?)" 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): ‘‘‘ 進行二次爬蟲，然後在新的頁面中對公司、薪資、工作經驗進行匹配 :param t: url地址 :param page: 當前匹配的頁數 ‘‘‘ html=self.load(t)#返回二次爬蟲的內容 parrten1=re.compile(‘<a\s+onclick=".*?"\s+href=".*?"\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>工作經驗：</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): ‘‘‘ 將最終爬去的內容寫入文件中 :param context: 匹配好的內容 :param page: 當前爬去的頁碼數 ‘‘‘ fileName = "di" + str(page) + "yehtml.txt" with open(fileName, "a") as file: file.writelines(context + "\n") if __name__ == ‘__main__‘: position=raw_input("請輸入職位：") workPlace=raw_input("請輸入工作地點：") z=zhiLian() z.spider(position,workPlace)
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+"\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("請輸入貼吧名：") startPage=raw_input("請輸入起始頁：") endPage=raw_input("請輸入終止頁：") t=teiba() t.spider(name,int(startPage),int(endPage))
Py爬蟲項目