很久没有写博客了，这段时间一直在搞风控的东西，过段时间我把风控的内容整理整理发出来大家一起研究研究。
这两天抽空写了两个python爬虫脚本，一个使用re，一个使用xpath。
直接上代码——基于re：
spider.py
# -*- coding:utf-8 -*- import urllib.request import re import tool import os import http.cookiejar # 抓取MOKO_MM class Spider: # 页面初始化 def __init__(self): self.siteURL = 'http://www.moko.cc/focus|list.action' self.tool = tool.Tool() # 获取索引页面的内容 def getPage(self, pageIndex): url = self.siteURL + "?type=4&curPage=" + str(pageIndex) request = urllib.request.Request(url) response = urllib.request.urlopen(request) return response.read().decode('utf-8') # 获取索引界面所有MM的信息，list格式 def getContents(self, pageIndex): page = self.getPage(pageIndex) pattern = re.compile( '<div class="subMainContent".*?<a href="(.*?)".*?subFocus-07.*?<img src="(.*?)".*?subFocus-08.*?<h1>(.*?)</h1>', re.S) items = re.findall(pattern, page) # item[0] 详情页链接 # item[1] 缩略图 # item[2] 标题 contents = [] for item in items: contents.append([item[0], item[1], item[2].replace(" ", "-").replace("|", "-").replace(".", "-").replace(":", "-")]) return contents # 获取MM个人详情页面 def getDetailPage(self, infoURL): def makeMyOpener(head={ 'accept-encoding': 'deflate, sdch', 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8', 'Accept-Language': 'zh-CN,zh;q=0.8', 'Cookie': 'JSESSIONID=58C82905AD36B5DFA8D4F1C98A2559DC; Hm_lvt_8d82e75c6168ba4bc0135a08edae2a2e=1488505496; Hm_lpvt_8d82e75c6168ba4bc0135a08edae2a2e', 'Referer': 'https://mm.taobao.com/687471686.htm', 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:51.0) Gecko/20100101 Firefox/51.0' }): cookie = http.cookiejar.CookieJar() opener = urllib.request.build_opener(urllib.request.HTTPCookieProcessor(cookie)) header = [] for key, value in head.items(): elem = (key, value) header.append(elem) opener.addheaders = header return opener oper = makeMyOpener() uop = oper.open(infoURL) data = uop.read().decode('utf-8') return data # response = urllib.request.urlopen(infoURL) # return response.read().decode('utf-8') # 获取个人文字简介 def getBrief(self, page): pattern = re.compile( '<div class="infoShow-12".*?<p align="center".*?<strong>(.*?)</strong>.*?<strong>(.*?)</strong>.*?<strong>(.*?)</strong>.*?<strong>(.*?)</strong>', re.S) items = re.findall(pattern, page) # item[0] 主页地址 # item[1] 头像 # item[2] 姓名 contents = [] for item in items: contents.append([item[0], item[1], item[2]]) return contents # result = re.search(pattern, page) # print(result.group()) # return self.tool.replace(result.group(1)) # 获取页面所有图片 def getAllImg(self, page): pattern = re.compile('<div class="infoShow-12">(.*?)<div class="infoShow-13">', re.S) # 个人信息页面所有代码 content = re.search(pattern, page) # 从代码中提取图片 patternImg = re.compile('<img.*?src="(.*?)"', re.S) images = re.findall(patternImg, content.group(1)) return images # 保存多张写真图片 def saveImgs(self, images, name): number = 1 print(u"发现", name, u"共有", len(images), u"张照片") for imageURL in images: splitPath = imageURL.split('.') splitPath = splitPath fTail = splitPath.pop() if len(fTail) > 3: fTail = "jpg" fileName = name + "/" + str(number) + "." + fTail self.saveImg(imageURL, fileName) number += 1 # 保存头像 def saveIcon(self, iconURL, name): splitPath = iconURL.split('.') fTail = splitPath.pop() fileName = name + "/icon." + fTail self.saveImg(iconURL, fileName) # 保存个人简介 def saveBrief(self, content, name): fileName = name + "/" + name + ".txt" f = open(fileName, "w+") print(u"正在保存信息为", fileName) # f.write(content.decode('utf-8')) f.write(content) # 保存图片地址页到各文件夹中 def saveToLocal(self, Li, name): fileName = name + "/" + "urlPage.txt" print(u"正在保存图片地址页：", fileName) # f.write(content.decode('utf-8')) # pre=pre.replace("[","") # pre=pre.replace("]","")+" " # print (pre) f = open(fileName, "w") f.write(Li) f.close() # 追加方式写入当前爬行的名字，后续调用 content = name + " " with open('url.txt', 'a') as url: url.write(content) url.close() print(name + u"追加完成！ ") # 传入图片地址，文件名，保存单张图片 def saveImg(self, imageURL, fileName): try: u = urllib.request.urlopen(imageURL) data = u.read() f = open(fileName, 'wb') f.write(data) print(u"正在保存的一张图片为", fileName) f.close() except urllib.request.URLError as e: print(e.reason) # 创建新目录 def mkdir(self, path): path = path.strip() # 判断路径是否存在 # 存在 True # 不存在 False isExists = os.path.exists(path) # 判断结果 if not isExists: # 如果不存在则创建目录 print(u"新建了名字叫做", path, u'的文件夹') # 创建目录操作函数 os.makedirs(path) return True else: # 如果目录存在则不创建，并提示目录已存在 print(u"名为", path, '的文件夹已经创建成功') return False # 将一页MOKO MM的信息保存起来 def savePageInfo(self, pageIndex): # 获取第一页MOKO MM列表 contents = self.getContents(pageIndex) for item in contents: # item[0]个人详情URL,item[1]头像URL,item[2]姓名 print(u"发现一位名叫", item[2], u"的信息") print(u"正在保存", item[2], "的信息") print(u"个人详情地址是", "http://www.moko.cc" + str(item[0])) # 个人详情页面的URL detailURL = "http://www.moko.cc" + str(item[0]) # 得到个人详情页面代码 detailPage = self.getDetailPage(detailURL) # 获取个人简介 # brief = self.getBrief(detailPage) # 获取所有图片列表 self.mkdir(item[2]) images = self.getAllImg(detailPage) spider.saveImgs(images, item[2]) # 保存个人简介 # self.saveBrief(brief.encode('utf-8'), item[2]) # self.saveBrief(brief, item[2]) # 保存图片地址页到本地 # self.saveToLocal(detailPage, item[2]) # 保存头像 self.saveIcon("https:" + str(item[1]), item[2]) # 删除旧名单(如果有) def deleteOldTxt(self): filename = 'url.txt' if os.path.exists(filename): os.remove(filename) print(" 发现旧名单，已删除 采集开始 ") # 传入起止页码，获取MM页面保存 def savePagesInfo(self, start, end): for i in range(start, end + 1): print(u"正在寻找第", i, u"个地方") self.savePageInfo(i) # 保存图片 # self.saveImgs(images,item[2]) # 读取名字list def openNameList(self): with open("url.txt", "r") as f: for line in f: line = line.strip() # line.split(",") # result.append(line) # result.append(line.split(",")) # s匹配空格与tab，s+表示至少一个 result = re.split(r's+', line) return result # 逐个调取文件夹下页面中地址来保存 def saveAll(self): i = spider.openNameList() for name in i: print("当前正在保存的是" + name + "的图片") filepath = name + "/urlPage.txt" with open(filepath, "r") as urlContent: urlContent = urlContent.read() images = spider.getAllImg(urlContent) spider.saveImgs(images, name) # 传入起止页码即可，在此传入了6,10,表示抓取第6到10页的MM spider = Spider() spider.deleteOldTxt() spider.savePagesInfo(1, 10)
tool.py
# -*- coding:utf-8 -*- import re # 处理页面标签类 class Tool: # 去除img标签,1-7位空格, removeImg = re.compile(r'<img.*?>| {1,7}| ') # 删除超链接标签 removeAddr = re.compile(r'<a.*?>|</a>') # 把换行的标签换为 replaceLine = re.compile(r'<tr>|<div>|</div>|</p>') # 将表格制表<td>替换为 replaceTD = re.compile(r'<td>') # 将换行符或双换行符替换为 replaceBR = re.compile(r'<br><br>|<br>') # 将其余标签剔除r removeExtraTag = re.compile(r'<.*?>') # 将多行空行删除 removeNoneLine = re.compile(r' +') # 删除 removeSpace = re.compile(r' ') def replace(self, x): x = re.sub(self.removeImg, "", x) x = re.sub(self.removeAddr, "", x) x = re.sub(self.replaceLine, " ", x) x = re.sub(self.replaceTD, " ", x) x = re.sub(self.replaceBR, " ", x) x = re.sub(self.removeExtraTag, "", x) x = re.sub(self.removeNoneLine, " ", x) x = re.sub(self.removeSpace, "", x) # strip()将前后多余内容删除 return x.strip()