简单Python爬虫的编写

最新推荐文章于 2024-02-16 10:53:15 发布

大圣猿

最新推荐文章于 2024-02-16 10:53:15 发布

阅读量188

点赞数 2

分类专栏： Python爬虫文章标签： Python 爬虫 BeautifulSoup库

本文链接：https://blog.csdn.net/qq_27964731/article/details/82454937

版权

Python爬虫专栏收录该内容

1 篇文章 0 订阅

订阅专栏

# -*- coding: utf-8 -*-
from urllib.request import urlopen
from bs4 import BeautifulSoup
import  re
import  datetime
import  random


def gethtml(url):
    html=urlopen(url)
    return html

def byclass(tag,css):
    namelist=bsObj.findAll(tag,css)
    return  namelist

html = gethtml("http://sydw.huatu.com/sc/")
bsObj = BeautifulSoup(html)
print(bsObj)
print("-------------------class search--------------------------")
namelist=bsObj.findAll("div",{"class":"list_top"})
print(namelist)
print("------------------- 过滤  --------------------------")
for name in namelist:
    print(name.get_text())

print("------------------- 元素的横向和纵向查找  --------------------------")

html=gethtml("http://www.pythonscraping.com/pages/page3.html")
obj=BeautifulSoup(html)
namelist=obj.find("table",{"id":"giftList"}).children
for name in namelist:
    print(name)

print("------------------- 兄弟标签处理 --------------------------")
namelist=obj.find("table",{"id":"giftList"}).tr.next_siblings
for name in  namelist:
    print(name)

print("------------------- 正则匹配 --------------------------")
#  *表示匹配前面的字符
namelist=obj.findAll("img",{"src":re.compile("\.\.\/img\/gifts\/img.*\.jpg")})
for name in  namelist:
    print(name)
    print("过滤属性："+name.attrs["src"])

print("------------------- 动态页面的爬询 --------------------------")
web=gethtml("http://en.wikipedia.org/wiki/Kevin_Bacon")
webobj=BeautifulSoup(web)
node=webobj.findAll("a")
for link in node:
    if "href" in link.attrs:
        print(link.attrs["href"])


random.seed(datetime.datetime.now())
def getlinks(articurl):
    html=urlopen("http://en.wikipedia.org"+articurl)
    bsObj=BeautifulSoup(html)
    return bsObj.findAll("div",{"id":"bodyContent"})\
        .findAll("a",href=re.compile("^(/wiki/)((?!:).)*$"))

    links = getlinks("/wiki/Kevin_Bacon",)
while len(links) > 0:
    newArticle = links[random.randint(0, len(links)-1)].attrs["href"]
    print(newArticle)
    links = getLinks(newArticle)