Python学习之爬虫案例

Posted on | In

Python学习之爬虫案例

– 直接上代码

python引入模块

1
2
import re
from urllib.request import urlopen

获取网页内容并返回

1
2
3
def getPage(url):
    response = urlopen(url)
    return response.read().decode('utf-8')

正则获取需要的内容

1
2
3
4
5
6
def parseHtml(s):
    ret = re.findall(
        '<li>.*?<span class="view">\s\W+(?P<vcount>\d+).*?<em>.*?</em>.*?</span>'
        '.*?<div class="a1">.*?<a href="(?P<href>.*?)">(?P<title>.*?)</a>.*?</div>.*?</li>', s, re.S
    )
    return ret

内容保存

1
2
3
4
5
6
def writefile(dbs):
    f = open(r'new.txt', "w+",encoding="utf-8")
    for i in dbs:
        print(i[0]+i[1]+i[2])
        f.writelines(i[0]+i[1]+i[2] + '\n')
    f.close()

启动调用方法

1
2
3
4
5
6
def main():
    url = "http://www.yichang100.com/"
    respones_html = getPage(url)
    ret = parseHtml(respones_html)
    writefile(ret)
main()