python爬虫学习之使用XPath解析开奖网站

实例需求：运用python语言爬取http://kaijiang.zhcw.com/zhcw/html/ssq/list_1.html这个开奖网站所有的信息，并且保存为txt文件。

实例环境：python3.7
　　　　　  BeautifulSoup库、XPath(需手动安装)
　　　　　  urllib库(内置的python库，无需手动安装)

实例网站：

　　第一步，点击链接http://kaijiang.zhcw.com/zhcw/html/ssq/list_1.html进入网站，查看网站基本信息，注意一共要爬取118页数据。

　　第二步，查看网页源代码，熟悉网页结构，标签等信息。

实例代码：

#encoding=utf-8
#pip install lxml
from bs4 import BeautifulSoup
import urllib.request
from lxml import etree

class GetDoubleColorBallNumber(object):
    def __init__(self):
        self.urls = []
        self.getUrls()
        self.items = self.spider(self.urls)
        self.pipelines(self.items)

    def getUrls(self):
        URL = r‘http://kaijiang.zhcw.com/zhcw/html/ssq/list.html‘
        htmlContent = self.getResponseContent(URL)
        soup = BeautifulSoup(htmlContent, ‘html.parser‘)
        tag = soup.find_all(‘p‘)[-1]
        pages = tag.strong.get_text()
        pages = ‘3‘
        for i in range(2, int(pages)+1):
            url = r‘http://kaijiang.zhcw.com/zhcw/html/ssq/list_‘ + str(i) + ‘.html‘
            self.urls.append(url)

    #3、	网络模块（NETWORK）
    def getResponseContent(self, url):
        try:
            response = urllib.request.urlopen(url)
        except urllib.request.URLError as e:
            raise e
        else:
            return response.read().decode("utf-8")

    #3、爬虫模块（Spider）
    def spider(self,urls):
        items = []
        for url in urls:
            try:
                html = self.getResponseContent(url)
                xpath_tree = etree.HTML(html)
                trTags = xpath_tree.xpath(‘//tr[not(@*)]‘)   # 匹配所有tr下没有任何属性的节点
                for tag in trTags:

                    # if tag.xpath(‘../html‘):
                    #     print("找到了html标签")
                    # if tag.xpath(‘/td/em‘):
                    #     print("****************")

                    #如果存在em子孙节点
                    if tag.xpath(‘./td/em‘):
                        item = {}
                        item[‘date‘] = tag.xpath(‘./td[1]/text()‘)[0]
                        item[‘order‘] = tag.xpath(‘./td[2]/text()‘)[0]
                        item[‘red1‘] = tag.xpath(‘./td[3]/em[1]/text()‘)[0]
                        item[‘red2‘] = tag.xpath(‘./td[3]/em[2]/text()‘)[0]
                        item[‘red3‘] = tag.xpath(‘./td[3]/em[3]/text()‘)[0]
                        item[‘red4‘] = tag.xpath(‘./td[3]/em[4]/text()‘)[0]
                        item[‘red5‘] = tag.xpath(‘./td[3]/em[5]/text()‘)[0]
                        item[‘red6‘] = tag.xpath(‘./td[3]/em[6]/text()‘)[0]
                        item[‘blue‘] = tag.xpath(‘./td[3]/em[7]/text()‘)[0]
                        item[‘money‘] = tag.xpath(‘./td[4]/strong/text()‘)[0]
                        item[‘first‘] = tag.xpath(‘./td[5]/strong/text()‘)[0]
                        item[‘second‘] = tag.xpath(‘./td[6]/strong/text()‘)[0]
                        items.append(item)
            except Exception as e:
                print(str(e))
                raise e
        return items

    def pipelines(self,items):
        fileName = u‘双色球.txt‘
        with open(fileName, ‘w‘) as fp:
            for item in items:
                fp.write(‘%s %s \t %s %s %s %s %s %s  %s \t %s \t %s %s \n‘
                      %(item[‘date‘],item[‘order‘],item[‘red1‘],item[‘red2‘],item[‘red3‘],item[‘red4‘],item[‘red5‘],item[‘red6‘],item[‘blue‘],item[‘money‘],item[‘first‘],item[‘second‘]))

if __name__ == ‘__main__‘:
    GDCBN = GetDoubleColorBallNumber()

实例结果：

原文地址：https://www.cnblogs.com/xiaoyh/p/10211646.html