Python网络爬虫实战：抓取电商商品数据示例

#! /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()