python XML實例
案例:使用XPath的爬蟲
現在我們用XPath來做一個簡單的爬蟲,我們嘗試爬取某個貼吧裏的所有帖子,並且將該這個帖子裏每個樓層發布的圖片下載到本地。
# tieba_xpath.py
#!/usr/bin/env python
# -*- coding:utf-8 -*-
import os
import urllib
import urllib2
from lxml import etree
class Spider:
def __init__(self):
self.tiebaName = raw_input("請需要訪問的貼吧:")
self.beginPage = int(raw_input("請輸入起始頁:"))
self.endPage = int(raw_input("請輸入終止頁:"))
self.url = ‘http://tieba.baidu.com/f‘
self.ua_header = {"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1 Trident/5.0;"}
# 圖片編號
self.userName = 1
def tiebaSpider(self):
for page in range(self.beginPage, self.endPage + 1):
pn = (page - 1) * 50 # page number
word = {‘pn‘ : pn, ‘kw‘: self.tiebaName}
word = urllib.urlencode(word) #轉換成url編碼格式(字符串)
myUrl = self.url + "?" + word
# 示例:http://tieba.baidu.com/f? kw=%E7%BE%8E%E5%A5%B3 & pn=50
# 調用 頁面處理函數 load_Page
# 並且獲取頁面所有帖子鏈接,
links = self.loadPage(myUrl) # urllib2_test3.py
# 讀取頁面內容
def loadPage(self, url):
req = urllib2.Request(url, headers = self.ua_header)
html = urllib2.urlopen(req).read()
# 解析html 為 HTML 文檔
selector=etree.HTML(html)
#抓取當前頁面的所有帖子的url的後半部分,也就是帖子編號
# http://tieba.baidu.com/p/4884069807裏的 “p/4884069807”
links = selector.xpath(‘//div[@class="threadlist_lz clearfix"][email protected]