网络爬虫(又被称为网页蜘蛛,网络机器人,在FOAF社区中间,更经常的称为网页追逐者),是一种按照一定的规则,自动的抓取万维网信息的程序或者脚本。
下面有一个示例代码,分享给大家:
#! /usr/bin/env python # encoding = 'utf-8'# Filename: spider_58center_sth.py from bs4 import BeautifulSoup import time import requests url_58 = 'http://nj.58.com/?PGTID=0d000000-0000-0c5c-ffba-71f8f3f7039e&ClickID=1' '' ' 用于爬取电商售卖信息: 例为58同城电脑售卖信息 '' ' def get_url_list(url): web_data = requests.get(url) soup = BeautifulSoup(web_data.text, 'lxml') url = soup.select('td.t > a[class="t"]') url_list = '' for link in url: link_n = link.get('href') if 'zhuanzhuan' in link_n: pass else : if 'jump' in link_n: pass else : url_list = url_list + 'n' + link_n print('url_list: %s' % url_list) return url_list# 分类获取目标信息 def get_url_info(): url_list = get_url_list(url_58) for url in url_list.split(): time.sleep(1) web_datas = requests.get(url) soup = BeautifulSoup(web_datas.text, 'lxml') type = soup.select('#head > div.breadCrumb.f12 > span:nth-of-type(3) > a') title = soup.select(' div.col_sub.mainTitle > h1') date = soup.select('li.time') price = soup.select('div.person_add_top.no_ident_top > div.per_ad_left > div.col_sub.summary > ul > ' 'li:nth-of-type(1) > div.su_con > span.price.c_f50') fineness = soup.select('div.col_sub.summary > u1 > li:nth-of-type(2) > div.su_con > span') area = soup.select('div.col_sub.summary > u1 > li:nth-of-type(3) > div.su_con > span') for typei, titlei, datei, pricei, finenessi, areai in zip(type, title, date, price, fineness, area): #做字典 data = { 'type': typei.get_text(), 'title': titlei.get_text(), 'date': datei.get_text(), 'price': pricei.get_text(), 'fineness': (finenessi.get_text()).strip(), 'area': list(areai.stripped_strings) } print(data) get_url_info()
爬取商城商品售卖信息
总结
以上就是本文关于Python探索之爬取电商售卖信息代码示例的全部内容,希望对大家有所帮助。感兴趣的朋友可以继续参阅本站:Python探索之自定义实现线程池、Python探索之ModelForm代码详解等,如有不足之处,欢迎留言指出。感谢朋友们对本站的支持!