您的位置 首页 linux安装软件

获取 wordpress 网站文章链接

import re
import bs4
import urllib.request

# url_home = 'http://www.5bug.wang/'  # 要采集的网站
url_home = 'https://www.baimeidashu.com/'  # 要采集的网站
url_pattern = url_home + '([\s\S]*)\.html'  # 正则表达式匹配文章页面,此处需完善为更好的写法
url_set = set()
url_cache = set()
url_count = 0
url_maxCount = 1000  # 最大采集数量


# 采集匹配文章内容的href标签
def spiderURL(url, pattern):
    html = urllib.request.urlopen(url).read().decode('utf8')
    soup = bs4.BeautifulSoup(html, 'html.parser')
    links = soup.find_all('a', href=re.compile(pattern))
    for link in links:
        if link['href'] not in url_cache:
            url_set.add(link['href'])  # 获取所有的 文章地址
    return soup


# 采集的过程  异常处理还需要完善,对于一些加了防采集的站,还需要处理header的,下次我们再学习
spiderURL(url_home, url_pattern)


while len(url_set) != 0:
    try:
        url = url_set.pop()
        url_cache.add(url)
        soup = spiderURL(url, url_pattern)
        title = soup.find('title').get_text()
        # print(title)
        # print(url)
        '''
        
<p class="entry-title"><a href="https://www.baimeidashu.com/7140.html">Linux文件目录命令(以及必须要掌握的几个目录)linux目录结构</a></p>

        '''
        ss = "<p class= " + "entry-title" + "><a href= "+ url +">" + title + "</a></p>"

        print(ss)

        file = open('test.txt', 'a')
        file.write(ss)

        file.write('\n')

        file.close()

    except Exception as e:
        print(url, e)
        continue
    else:
        url_count += 1
    finally:
        if url_count == url_maxCount:
            break

print('一共采集了: ' + str(url_count) + ' 条数据')

欢迎来撩 : 汇总all

白眉大叔

关于白眉大叔linux云计算: 白眉大叔

热门文章