spider_douban_events.py

# coding=utf-8

from pyquery import PyQuery as pq
import sys

def main():
    reload(sys)
    sys.setdefaultencoding('utf-8')

    page = 0
    tot = 0
    while True:
        d = pq(url='http://shanghai.douban.com/events/future-all?start=%s' % (page*10))

        if d('p.no-result').text() != None:
            print 'Total results: %s' % tot
            break

        for i in range(0, 10):
            li = d("ul.events-list li:eq(%s)" % i)
            if li.text() == None:
                break
            title = li("div.title").text()
            location = li("meta").attr("content")
            counts = li("p.counts").text()
            counts_join = counts.split('人参加')[0].strip()
            counts_interest = counts.split(' ')[1].split('人感兴趣')[0].strip()
            print title
            tot = tot + 1

        page = page + 1

if __name__ == "__main__":
    main()

我主要是抓了标题、地点、参加和感兴趣的人数这四个数据，输出了title。

最后一个bug是，豆瓣会封爬虫，所以打算限制一下每分钟的访问次数。