Python爬虫编程实例（一）

• 本文主要介绍三个实例：分别是基于bs4库的中国大学排名定向爬取、基于Xpath的丁香园用户和回复内容爬取、以及基于re库的淘宝商品比价定向爬虫
• 学习交流请联系 [email protected]

中国大学排名定向爬取

• 爬取url：http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html
• 爬取思路：
  1. 从网络上获取大学排名网页内容
  2. 提取网页内容中信息到合适的数据结构（二维数组）-排名，学校名称，总分
  3. 利用数据结构展示并输出结果

# 导入库
import requests
from bs4 import BeautifulSoup
import bs4

# 第一步：从网络上获取大学排名网页内容
def getHTMLText(url):
    try:
        r = requests.get(url,timeout=30)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return ""

# 第二步：提取网页内容到合适的数据结构
def fillUnivList(ulist, html):
    soup = BeautifulSoup(html, "html.parser")
    for tr in soup.find('tbody').children: 
        if isinstance(tr, bs4.element.Tag):
            tds = tr('td')             
            ulist.append([tds[0].string, tds[1].string, tds[2].string,tds[3].string])   

#  第三步：展示输出结果
def printUnivList(ulist, num):
    tplt = "{0:^10}\t{1:{4}^8}\t{2:6}\t{3:10}"
    print(tplt.format("排名","学校名称","城市","总分",chr(12288)))
    # 填充中文空格
    for i in range(num):
        u=ulist[i]
        print(tplt.format(u[0],u[1],u[2],u[3],chr(12288)))
 
 # 执行
def main():
    uinfo = []
    url ='http://www.zuihaodaxue.cn/zuihaodaxuepaiming2019.html'
    html = getHTMLText(url)
    fillUnivList(uinfo, html)
    printUnivList(uinfo, 30) # 排名前30大学信息

if __name__ == "__main__":
    main()

丁香园用户名和回复内容爬取

• 爬取url：http://www.dxy.cn/bbs/thread/626626#626626
• 爬取思路：
  1. 获取url的html,lxml解析html
  2. 利用Xpath表达式获取user和content
  3. 保存爬取的内容

# 导入库
from lxml import etree
import requests

url = "http://www.dxy.cn/bbs/thread/626626#626626"

req = requests.get(url)
html = req.text
tree = etree.HTML(html)

# 利用Xpath表达式获取user和content
user = tree.xpath('//div[@class="auth"]/a/text()')
content = tree.xpath('//td[@class="postbody"]')

# 保存爬取的内容
results = []
for i in range(0, len(user)):
    results.append(user[i].strip() + ":  " + content[i].xpath('string(.)').strip())

# 打印爬取的结果
for i,result in zip(range(0, len(user)),results):
    print("user"+ str(i+1) + "-" + result)
    print("-"*100)

淘宝商品比价定向爬虫

• 爬取url：https://s.taobao.com/search?q=书包&js=1&stats_click=search_radio_all%25
• 爬取思路：
  1. 提交商品搜索请求，循环获取页面
  2. 对于每个页面，提取商品名称和价格信息
  3. 将信息输出到屏幕上

# 导入包
import requests
import re

# 第一步：提交商品搜索请求，循环获取页面
def getHTMLText(url):
    """
    请求获取html，（字符串）
    :param url: 爬取网址
    :return: 字符串
    """
    try:
        # 添加头信息,
        kv = {
            'cookie': 'thw=cn; v=0; t=ab66dffdedcb481f77fd563809639584; cookie2=1f14e41c704ef58f8b66ff509d0d122e; _tb_token_=5e6bed8635536; cna=fGOnFZvieDECAXWIVi96eKju; unb=1864721683; sg=%E4%B8%8B3f; _l_g_=Ug%3D%3D; skt=83871ef3b7a49a0f; cookie1=BqeGegkL%2BLUif2jpoUcc6t6Ogy0RFtJuYXR4VHB7W0A%3D; csg=3f233d33; uc3=vt3=F8dBy3%2F50cpZbAursCI%3D&id2=UondEBnuqeCnfA%3D%3D&nk2=u%2F5wdRaOPk21wDx%2F&lg2=VFC%2FuZ9ayeYq2g%3D%3D; existShop=MTU2MjUyMzkyMw%3D%3D; tracknick=%5Cu4E36%5Cu541B%5Cu4E34%5Cu4E3F%5Cu5929%5Cu4E0B; lgc=%5Cu4E36%5Cu541B%5Cu4E34%5Cu4E3F%5Cu5929%5Cu4E0B; _cc_=WqG3DMC9EA%3D%3D; dnk=%5Cu4E36%5Cu541B%5Cu4E34%5Cu4E3F%5Cu5929%5Cu4E0B; _nk_=%5Cu4E36%5Cu541B%5Cu4E34%5Cu4E3F%5Cu5929%5Cu4E0B; cookie17=UondEBnuqeCnfA%3D%3D; tg=0; enc=2GbbFv3joWCJmxVZNFLPuxUUDA7QTpES2D5NF0D6T1EIvSUqKbx15CNrsn7nR9g%2Fz8gPUYbZEI95bhHG8M9pwA%3D%3D; hng=CN%7Czh-CN%7CCNY%7C156; mt=ci=32_1; alitrackid=www.taobao.com; lastalitrackid=www.taobao.com; swfstore=97213; x=e%3D1%26p%3D*%26s%3D0%26c%3D0%26f%3D0%26g%3D0%26t%3D0%26__ll%3D-1%26_ato%3D0; uc1=cookie16=UtASsssmPlP%2Ff1IHDsDaPRu%2BPw%3D%3D&cookie21=UIHiLt3xThH8t7YQouiW&cookie15=URm48syIIVrSKA%3D%3D&existShop=false&pas=0&cookie14=UoTaGqj%2FcX1yKw%3D%3D&tag=8&lng=zh_CN; JSESSIONID=A502D8EDDCE7B58F15F170380A767027; isg=BMnJJFqj8FrUHowu4yKyNXcd2PXjvpa98f4aQWs-RbDvsunEs2bNGLfj8BYE6lWA; l=cBTDZx2mqxnxDRr0BOCanurza77OSIRYYuPzaNbMi_5dd6T114_OkmrjfF96VjWdO2LB4G2npwJ9-etkZ1QoqpJRWkvP.; whl=-1%260%260%261562528831082',
            'user-agent': 'Mozilla/5.0'
        }
        r = requests.get(url, timeout=30, headers=kv)
        # r = requests.get(url, timeout=30)
        # print(r.status_code)
        r.raise_for_status()
        r.encoding = r.apparent_encoding
        return r.text
    except:
        return "爬取失败"

# 第二步：获取每个页面的商品名称和价格信息
def parsePage(glist, html):
    '''
    解析网页，搜索需要的信息
    :param glist: 列表作为存储容器
    :param html: 由getHTMLText()得到的
    :return: 商品信息的列表
    '''
    try:
        price_list = re.findall(r'', html)
        name_list = re.findall(r'', html)
        for i in range(len(price_list)):
            price = eval(price_list[i].split(":")[1])  
            name = eval(name_list[i].split(":")[1])
            glist.append([price, name])
    except:
        print("解析失败")

# 第三步：将信息传到屏幕上
def printGoodList(glist):
    tplt = "{0:^4}\t{1:^6}\t{2:^10}"
    print(tplt.format("序号", "商品价格", "商品名称"))
    count = 0
    for g in glist:
        count = count + 1
        print(tplt.format(count, g[0], g[1]))
# 根据页面url的变化寻找规律，构建爬取url
goods_name = "书包"  # 搜索商品类型
start_url = "https://s.taobao.com/search?q=" + goods_name
info_list = []
page = 3  # 爬取页面数量
count = 0
for i in range(page):
    count += 1
    try:
        url = start_url + "&s=" + str(44 * i)
        html = getHTMLText(url)  # 爬取url
        parsePage(info_list, html) #解析HTML和爬取内容
        print("\r爬取页面当前进度: {:.2f}%".format(count * 100 / page), end="")  # 进度条
    except:
        continue
printGoodList(info_list)