爬虫篇-博客园搜索爬取

爬取用户提交关键字在博客园搜索出来的文章,一页十篇,共50页,获取标题,内容,发表时间,推荐量,评论量,浏览量

写入sql server数据库,代码如下;

import requests
from lxml import etree
import pymssql
import time

# 连接sql server数据库
conn = pymssql.connect(host='127.0.0.1',
                       user='sa',
                       password='root',
                       database='a',
                       charset='utf8')
cursor = conn.cursor()
headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36',
    'cookie': '_ga=GA1.2.789692814.1575245968; _gid=GA1.2.90574348.1575245968; __gads=ID=d0b3d037d343ea7f:T=1575246122:S=ALNI_MYb3-Nqsf59wLf_5kAyYqYllV7EFA; _gat=1; .Cnblogs.AspNetCore.Cookies=CfDJ8DeHXSeUWr9KtnvAGu7_dX-Wfut1-dgX_yW1t_fPBSG6ejwby5on7dPqagwvw_WdjyzxkSv4BwoUWPbClu4VNcySbHU5xW1f4vpuOB4NET3TigRH9T3mlgNwIWy7oqLFygXjQxNj2gkFzpDx7Yq8T7HJOmxg30lx50dN4ssnGTWVCTppMnHJT1NyfQs58HorucZThRwEjTxDMdcAI_VoGbd-EmMOUT9h-fLvnQ_hn4b8lQ9evYMG4n9nmmArBnhf3wNo-RKb7TgMCx6QUWWIbYXp2M2TjzG3uzbO3rnEljkTL1cVEB6My97ZQfjLRe27RbArxp4wltsXi4WkBcNTQAXyI2SpiFZYCcBZTxT_uC-Z5Phphjs-sl1_iu7sIR-8m0qysad-BuKdS6Qwvj5qlJt1JCJbi_WFH6Dzs_rgJvn0DfPQE50sAlHOs6Dhgqc7N-YDVqpSphJDRlRkIM6JBH8Pq6EZ8S0IRbZsdkIqiJ54CD-H5G5Hx9oATlEakAqDnWyZ4LlBVyu1wkne48R5usxkmITyZ1PDWwHC5pKRKxfelXDoR05REO4GDOXhXxG5XEZeYA1rWdJI7AKnIM5RM9Y; .CNBlogsCookie=E4793F450C4325E3C9EF21B78B1DE43F6258C9FD5951338859D96A5EC8795064AB518501755136F3A4CB1CE647EBD2CC352C1E9EBDC6E460B6320E9F62F083A52A635A4651A3D1082631D55FCE58E283B97D016E61DC411E094F6EA9A9CF9A59A292C16F'
}

"""
标题,内容,发表时间,推荐量,评论量,浏览量
"""
# 写入数据库
def insert_sqlserver(key,data):
    try:
        cursor.executemany(
            "insert into {}(title,contents,create_time,view_count,comment_count,good_count) VALUES(%s,%s,%s,%s,%s,%s)".format(key),data
        )
        conn.commit()
    except Exception as e:
        print(e,'写入数据库时错误')


# 获取数据
def get_all(key,url):
    for i in range(1,51):
        next_url = url+'&pageindex=%s'%i
        res = requests.get(next_url,headers=headers)
        response = etree.HTML(res.text)
        details = response.xpath('//div[@class="searchItem"]')
        data = []
        print(next_url)
        for detail in details:
            try:
                detail_url = detail.xpath('./h3/a[1]/@href')
                good = detail.xpath('./div/span[3]/text()')
                comments = ['0' if not detail.xpath('./div/span[4]/text()') else detail.xpath('./div/span[4]/text()')[0]]
                views = ['0' if not detail.xpath('./div/span[5]/text()') else detail.xpath('./div/span[5]/text()')[0]]
                res = requests.get(detail_url[0],headers=headers)
                response = etree.HTML(res.text)
                title = response.xpath('//a[@id="cb_post_title_url"]/text()')[0]
                contents = response.xpath('//div[@id="post_detail"]') if not response.xpath('//div[@class="postbody"]') else response.xpath('//div[@class="postbody"]')
                content = etree.tounicode(contents[0],method='html')
                create_time = response.xpath('//span[@id="post-date"]/text()')[0]
                print(detail_url[0],good[0],comments[0],views[0],title,create_time)
                data.append((title,content,create_time,views[0],comments[0],good[0]))
                time.sleep(2)
            except Exception as e:
                print(e,'获取数据错误')
        insert_sqlserver(key,data)

# //*[@id="searchResult"]/div[2]/div[2]/h3/a

# 主函数并创建数据表
def main(key,url):
    cursor.execute("""
    if object_id('%s','U') is not null
        drop table %s
    create table %s(
        id int not null primary key IDENTITY(1,1),
        title varchar(500),
        contents text,
        create_time datetime,
        view_count varchar(100),
        comment_count varchar(100),
        good_count varchar(100)
    )
    """%(key,key,key))
    conn.commit()
    get_all(key,url)




if __name__ == '__main__':
    key = 'python'
    url = 'https://zzk.cnblogs.com/s?t=b&w=%s'%key
    main(key,url)
    conn.close()

查看数据库内容:

爬虫篇-博客园搜索爬取_第1张图片

 

 done

你可能感兴趣的:(爬虫篇-博客园搜索爬取)