网易新闻排行榜爬虫

一些说明：

1. 使用urllib或requests包来爬取页面。
2. 使用正则表达式分析一级页面，使用Xpath来分析二级页面。
3. 将得到的标题和链接，保存为本地文件。

NewsSpider.py代码:

import os
import sys
import urllib
import requests
import re
from lxml import etree


def StringListSave(save_path, filename, slist):
    if not os.path.exists(save_path):
        os.makedirs(save_path)
    path = save_path+"/"+filename+".txt"
    with open(path, "w+") as fp:
        for s in slist:
            fp.write("%s\t\t%s\n" % (s[0].encode("utf8").decode('utf-8'), s[1].encode("utf8").decode('utf-8')))

def Page_Info(myPage):
    '''Regex'''
    mypage_Info = re.findall(r'<div class="titleBar" id=".*?"><h2>(.*?)</h2><div class="more"><a href="(.*?)">.*?</a></div></div>', myPage, re.S)
    return mypage_Info

def New_Page_Info(new_page):
    '''Regex(slowly) or Xpath(fast)'''
    # new_page_Info = re.findall(r'<td class=".*?">.*?<a href="(.*?)\.html".*?>(.*?)</a></td>', new_page, re.S)
    # # new_page_Info = re.findall(r'<td class=".*?">.*?<a href="(.*?)">(.*?)</a></td>', new_page, re.S) # bugs
    # results = []
    # for url, item in new_page_Info:
    #     results.append((item, url+".html"))
    # return results
    dom = etree.HTML(new_page)
    new_items = dom.xpath('//tr/td/a/text()')
    new_urls = dom.xpath('//tr/td/a/@href')
    assert(len(new_items) == len(new_urls))
    return zip(new_items, new_urls)

def Spider(url):
    i = 0
    print("下载中 ", url)
    myPage = requests.get(url).content.decode("gbk")
    # myPage = urllib2.urlopen(url).read().decode("gbk")
    myPageResults = Page_Info(myPage)
    save_path = u"网易新闻抓取"
    filename = str(i)+"_"+u"新闻排行榜"
    StringListSave(save_path, filename, myPageResults)
    i += 1
    for item, url in myPageResults:
        print("下载中 ", url)
        new_page = requests.get(url).content.decode("gbk")
        # new_page = urllib2.urlopen(url).read().decode("gbk")
        newPageResults = New_Page_Info(new_page)
        filename = str(i)+"_"+item
        StringListSave(save_path, filename, newPageResults)
        i += 1


if __name__ == '__main__':
    print("开始")
    start_url = "http://news.163.com/rank/"
    Spider(start_url)
    print("结束")

运行结果如图:

---

---

---