糗事百科实例

爬取糗事百科段子，页面的URL是 http://www.qiushibaike.com/8hr/page/

1. 使用requests获取页面信息，用XPath 做数据提取

2. 获取每个帖子里的用户头像链接、用户姓名、段子内容、点赞次数和评论次数

 1 # -*- coding:utf-8 -*-
 2 import requests
 3 from lxml import etree
 4 
 5 def loadPage(url):
 6     headers = {
 7         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36',
 8         'Accept-Language': 'zh-CN,zh;q=0.8'}
 9     try:
10         response = requests.get(url, headers=headers)
11         resHtml = response.text
12         html = etree.HTML(resHtml)
13         result = html.xpath('//div[contains(@id,"qiushi_tag")]')
14         for site in result:
15             item = {}
16             imgUrl = site.xpath('./div/a/img/@src')[0].encode('utf-8')
17             #username = site.xpath('.//img/@alt')[0].encode('utf-8')
18             username = site.xpath('.//h2')[0].text
19             content = site.xpath('.//div[@class="content"]/span')[0].text.strip().encode('utf-8')
20             # 投票次数
21             vote = site.xpath('.//i')[0].text
22             #print site.xpath('.//*[@class="number"]')[0].text
23             # 评论信息
24             comments = site.xpath('.//i')[1].text
25             print imgUrl, username, content, vote, comments
26     except Exception, e:
27         print e
28 
29 def qiushiSpider(url, beginPage, endPage):
30     """
31         作用：贴吧爬虫调度器，负责组合处理每个页面的url
32         url : 贴吧url的前部分
33         beginPage : 起始页
34         endPage : 结束页
35     """
36     for page in range(beginPage, endPage + 1):
37         pn = page
38         fullurl = url + str(pn)
39         #print fullurl
40         loadPage(fullurl)
41         #print html
42 
43 if __name__ == "__main__":
44     beginPage = int(raw_input("请输入起始页："))
45     endPage = int(raw_input("请输入结束页："))
46     #page = 1
47     url = 'http://www.qiushibaike.com/8hr/page/'
48     qiushiSpider(url, beginPage, endPage)

 

 保存到 json 文件内

 1 #!/usr/bin/env python
 2 # -*- coding:utf-8 -*-
 3 
 4 import urllib2
 5 import json
 6 from lxml import etree
 7 
 8 
 9 def loadPage(url):
10     
11     headers = {"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;"}
12 
13     request = urllib2.Request(url, headers = headers)
14     html = urllib2.urlopen(request).read()
15     # 响应返回的是字符串，解析为HTML DOM模式 text = etree.HTML(html)
16 
17     text = etree.HTML(html)
18     # 返回所有段子的结点位置，contains()模糊查询方法，第一个参数是要匹配的标签，第二个参数是标签名部分内容
19     node_list = text.xpath('//div[contains(@id, "qiushi_tag")]')
20 
21     items ={}
22     for node in node_list:
23         # xpath返回的列表，这个列表就这一个参数，用索引方式取出来，用户名
24         username = node.xpath('.//img/@alt')[0]
25         # 图片连接
26         image = node.xpath('.//div[@class="thumb"]//@src')#[0]
27         # 取出标签下的内容,段子内容
28         content = node.xpath('.//div[@class="content"]/span')[0].text
29         # 取出标签里包含的内容，点赞
30         zan = node.xpath('.//i')[0].text
31         # 评论
32         comments = node.xpath('.//i')[1].text
33 
34         items = {
35             "username" : username,
36             "image" : image,
37             "content" : content,
38             "zan" : zan,
39             "comments" : comments
40         }
41 
42         with open("qiushi.json", "a") as f:
43             f.write(json.dumps(items, ensure_ascii = False).encode("utf-8") + "\n")
44 
45 def qiushiSpider(url, beginPage, endPage):
46     """
47         作用：贴吧爬虫调度器，负责组合处理每个页面的url
48         url : 贴吧url的前部分
49         beginPage : 起始页
50         endPage : 结束页
51     """
52     for page in range(beginPage, endPage + 1):
53         pn = page
54         fullurl = url + str(pn)
55         #print fullurl
56         loadPage(fullurl)
57         #print html
58 
59 if __name__ == "__main__":
60     beginPage = int(raw_input("请输入起始页："))
61     endPage = int(raw_input("请输入结束页："))
62     #page = 1
63     url = 'http://www.qiushibaike.com/8hr/page/'
64     qiushiSpider(url, beginPage, endPage)

 在python3中爬取糗事百科段子：

 1 import requests
 2 import json
 3 from lxml import etree
 4 from urllib import parse
 5 
 6 
 7 def loadPage(url):
 8     
 9     headers = {"User-Agent" : "Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0;"}
10 
11     response = requests.get(url, headers = headers)
12     html = response.content
13     # 响应返回的是字符串，解析为HTML DOM模式 text = etree.HTML(html)
14 
15     text = etree.HTML(html)
16     # 返回所有段子的结点位置，contains()模糊查询方法，第一个参数是要匹配的标签，第二个参数是标签名部分内容
17     node_list = text.xpath('//div[contains(@id, "qiushi_tag")]')
18 
19     items ={}
20     for node in node_list:
21         # xpath返回的列表，这个列表就这一个参数，用索引方式取出来，用户名
22         username = node.xpath('.//img/@alt')[0]
23         # 图片连接
24         image = node.xpath('.//div[@class="thumb"]//@src')#[0]
25         # 取出标签下的内容,段子内容
26         content = node.xpath('.//div[@class="content"]/span')[0].text
27         # 取出标签里包含的内容，点赞
28         zan = node.xpath('.//i')[0].text
29         # 评论
30         comments = node.xpath('.//i')[1].text
31 
32         items = {
33             "username" : username,
34             "image" : image,
35             "content" : content,
36             "zan" : zan,
37             "comments" : comments
38         }
39 
40         with open("qiushi.json", "a") as f:
41             #f.write(json.dumps(items, ensure_ascii = False).encode("utf-8") + "\n")
42             f.write(json.dumps(items, ensure_ascii = False) + "\n")
43 def qiushiSpider(url, beginPage, endPage):
44     """
45         作用：贴吧爬虫调度器，负责组合处理每个页面的url
46         url : 贴吧url的前部分
47         beginPage : 起始页
48         endPage : 结束页
49     """
50     for page in range(beginPage, endPage + 1):
51         pn = page
52         fullurl = url + str(pn)
53         #print(fullurl)
54         loadPage(fullurl)
55         #print(html)
56 
57 if __name__ == "__main__":
58     beginPage = int(input("请输入起始页："))
59     endPage = int(input("请输入结束页："))
60     #page = 1
61     url = 'http://www.qiushibaike.com/8hr/page/'
62     qiushiSpider(url, beginPage, endPage)

 

 

改进版

 1 # coding=utf-8
 2 import requests
 3 from lxml import etree
 4 import time
 5 
 6 class QiuBai:
 7     def __init__(self):
 8         self.temp_url = "http://www.qiushibaike.com/8hr/page/{}"
 9         self.headers = {"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36"}
10 
11     def get_url_list(self):
12         '''准备url地址的刘表'''
13         return [self.temp_url.format(i) for i in range(1,14)]
14 
15     def parse_url(self,url):
16         '''发送请求，获取响应'''
17         response = requests.get(url,headers=self.headers)
18         return response.content.decode()
19 
20     def get_content_list(self,html_str):
21         '''提取数据'''
22         html = etree.HTML(html_str)
23         div_list = html.xpath("//div[@id='content-left']/div")
24         content_list = []
25         for div in div_list:
26             item = {}
27             item["user_name"] = div.xpath(".//h2/text()")[0].strip()
28             item["content"] = [i.strip() for i in div.xpath(".//div[@class='content']/span/text()")]
29             content_list.append(item)
30         return content_list
31 
32     def save_content_list(self,content_list): 
33         '''保存'''
34         for content in content_list:
35             print(content)
36 
37     def run(self):#实现做主要逻辑
38         #1. 准备url列表
39         url_list = self.get_url_list()
40         #2. 遍历发送请求，获取响应
41         for url in url_list:
42             html_str = self.parse_url(url)
43             #3. 提取数据
44             content_list = self.get_content_list(html_str)
45             #4. 保存
46             self.save_content_list(content_list)
47 
48 
49 if __name__ == '__main__':
50     t1 = time.time()
51     qiubai = QiuBai()
52     qiubai.run()
53     print("total cost:",time.time()-t1)