实战——百度贴吧爬虫

最新推荐文章于 2020-03-02 15:53:20 发布

原创最新推荐文章于 2020-03-02 15:53:20 发布 · 380 阅读

1 ·

CC 4.0 BY-SA版权

爬虫专栏收录该内容

2 篇文章

订阅专栏

问题来源，因为自己正在学习，而这份代码恰好因为许多的原因而不能够运行，所以我就趁着这个计划将其修正，加深自己对于知识的理解和增值见识。
最初的代码

#-*-coding:utf8-*-
from lxml import etree
from multiprocessing.dummy import Pool as ThreadPool
import requests
import json
import sys

reload(sys)

sys.setdefaultencoding('utf-8')

'''重新运行之前请删除content.txt，因为文件操作使用追加方式，会导致内容太多。'''

def towrite(contentdict):
    f.writelines(u'回帖时间:' + str(contentdict['topic_reply_time']) + '\n')
    f.writelines(u'回帖内容:' + unicode(contentdict['topic_reply_content']) + '\n')
    f.writelines(u'回帖人:' + contentdict['user_name'] + '\n\n')

def spider(url):
    html = requests.get(url)
    selector = etree.HTML(html.text)
    content_field = selector.xpath('//div[@class="l_post l_post_bright "]')
    item = {}
    for each in content_field:
        reply_info = json.loads(each.xpath('@data-field')[0].replace('&quot',''))
        author = reply_info['author']['user_name']
        content = each.xpath('div[@class="d_post_content_main"]/div/cc/div[@class="d_post_content j_d_post_content "]/text()')[0]
        reply_time = reply_info['content']['date']
        print content
        print reply_time
        print author
        item['user_name'] = author
        item['topic_reply_content'] = content
        item['topic_reply_time'] = reply_time
        towrite(item)

if __name__ == '__main__':
    pool = ThreadPool(4)
    f = open('content.txt','a')
    page = []
    for i in range(1,21):
        newpage = 'http://tieba.baidu.com/p/3522395718?pn=' + str(i)
        page.append(newpage)

    results = pool.map(spider, page)
    pool.close()
    pool.join()
    f.close()