|
| 1 | +# -*- coding: utf-8 -*- |
| 2 | + |
| 3 | +import re |
| 4 | +import requests |
| 5 | +import time |
| 6 | + |
| 7 | + |
| 8 | +# 定义一个Tool类，方便用replace方法把换行符等删除 |
| 9 | +class Tool(): |
| 10 | + def replace(self, x): |
| 11 | + x = re.sub(re.compile('<br>|</br>|<br/>'), "", x) |
| 12 | + return x.strip() |
| 13 | + |
| 14 | + |
| 15 | +# 定义一个Spider类 |
| 16 | +class Spider(object): |
| 17 | + # 初始化参数 |
| 18 | + def __init__(self): |
| 19 | + self.siteURL = 'http://www.qiushibaike.com/' |
| 20 | + self.tool = Tool() |
| 21 | + |
| 22 | + # 获取网页源码 |
| 23 | + def getSource(self, url): |
| 24 | + user_agent = 'Mozilla/5.0 (Windows NT 6.2; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/45.0.2454.101 Safari/537.36' |
| 25 | + headers = {'User_agent': user_agent} |
| 26 | + r = requests.get(url, headers=headers) |
| 27 | + result = r.text |
| 28 | + return result |
| 29 | + |
| 30 | + # 获取详情页信息，并循环打印输出 |
| 31 | + def getDetailPage(self, detailURL): |
| 32 | + source = self.getSource(detailURL) |
| 33 | + pattern = re.compile( |
| 34 | + '<div class="author.*?<h2>(.*?)</h2>.*?Icon">(.*?)</div>.*?<div class="content">.*?<span>(.*?)</span>.*?<span.*?stats-vote.*?number">(.*?)</i>.*?stats-comments.*?number">(.*?)</i>.*?up.*?number hidden">(.*?)</span>.*?down.*?number hidden">(.*?)</span>', |
| 35 | + re.S) |
| 36 | + items = re.findall(pattern, source) |
| 37 | + number = 1 |
| 38 | + for item in items: |
| 39 | + print |
| 40 | + u'' |
| 41 | + print |
| 42 | + number, u'楼', u'\n楼主：', item[0], u'', item[1], u'岁', u'\n发言:', self.tool.replace(item[2]), u'\n好笑：', item[ |
| 43 | + 3], u'\n评论：', item[4], u'\n赞：', item[5], u'\n踩：', item[6] |
| 44 | + time.sleep(0.1) |
| 45 | + number += 1 |
| 46 | + return items |
| 47 | + |
| 48 | + # 保存信息写入文件 |
| 49 | + def saveDetailPage(self, data, name): |
| 50 | + fileName = 'page' + name + '.' + 'txt' |
| 51 | + f = open(fileName, 'wb') |
| 52 | + f.write(data.encode('utf-8')) |
| 53 | + print |
| 54 | + u'', u'成功将数据保存入文件', fileName |
| 55 | + f.close() |
| 56 | + |
| 57 | + # 对一页的操作 |
| 58 | + def OnePage(self, detailURL, name): |
| 59 | + data = self.getDetailPage(detailURL) |
| 60 | + self.saveDetailPage(str(data), str(name)) |
| 61 | + |
| 62 | + # 对很多页的操作 |
| 63 | + # 分两种情况讨论，start页等于1\start页大于1 |
| 64 | + def getAllPage(self, start, end): |
| 65 | + if start == 1: |
| 66 | + print |
| 67 | + u'正在获取第1页的数据...' |
| 68 | + detailURL = self.siteURL |
| 69 | + self.OnePage(detailURL, start) |
| 70 | + number = 2 |
| 71 | + for page in range(2, end + 1): |
| 72 | + print |
| 73 | + u'正在获取第', number, u'页的数据...' |
| 74 | + detailURL = self.siteURL + '8hr/page/' + str(page) + '/?s=4964625' |
| 75 | + self.OnePage(detailURL, number) |
| 76 | + time.sleep(2) |
| 77 | + number += 1 |
| 78 | + if number == end + 1: |
| 79 | + print |
| 80 | + u'', u'\n加载结束！' |
| 81 | + return False |
| 82 | + |
| 83 | + elif start > 1: |
| 84 | + number = start |
| 85 | + for page in range(start, end + 1): |
| 86 | + print |
| 87 | + u'', u'\n正在获取第', number, u'页的数据...' |
| 88 | + detailURL = self.siteURL + '8hr/page/' + str(page) + '/?s=4964625' |
| 89 | + self.OnePage(detailURL, number) |
| 90 | + time.sleep(2) |
| 91 | + number += 1 |
| 92 | + if number == end + 1: |
| 93 | + print |
| 94 | + u'', u'加载结束！' |
| 95 | + return False |
| 96 | + |
| 97 | + |
| 98 | +spider = Spider() |
| 99 | +spider.getAllPage(start=int(input('请输入起始页数：')), end=int(input('请输入结束页数'))) |
0 commit comments