爬虫-find_all()和find()方法

最新推荐文章于 2025-02-21 00:05:49 发布

zjb5599

最新推荐文章于 2025-02-21 00:05:49 发布

阅读量3.1k

点赞数 3

分类专栏：爬虫

本文链接：https://blog.youkuaiyun.com/zjb5599/article/details/106342435

版权

爬虫专栏收录该内容

14 篇文章

订阅专栏

1. find_all()和find()

find_all()⽅法以列表形式返回所有的搜索到的标签数据。
find()⽅法返回搜索到的第⼀条数据
find_all(self, name=None, attrs={}, recursive=True, text=None,
limit=None, **kwargs)
name : tag 名称
attrs ：标签的属性
recursive : 是否递归
text : 文本内容
limit : 限制返回的条数
**kwargs ：不定长参数以关键字来传参

from bs4 import BeautifulSoup
html_doc = """
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>
<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>
<p class="story">...</p>
"""
soup=BeautifulSoup(html_doc,'lxml')
a_tags=soup.find_all('a')
 print(a_tags)
 p_tags=soup.find_all('p','title')
 print(p_tags)
 print(soup.find_all(id='link1'))
 print(soup.find_all('a',limit=3))
 print(soup.a)
 print(soup.find('a'))
print(soup.find_all('a',recursive=True))
#print(soup.find_all('a',limit=1))[0]

2.find_parents() find_parent() find_next_siblings() find_next_sibling()

find_parents() 搜索所有⽗亲
find_parrent() 搜索单个⽗亲
find_next_siblings()搜索所有兄弟
find_next_sibling()搜索单个兄弟

title_tag=soup.title
print(title_tag.find_parent('head'))#<head><title>The Dormouse's story</title></head>
print(title_tag.find_parents('head'))
s=soup.find(text='Elsie')
print(s.find_previous('p'))
print(s.find_parents('p'))
a_tag=soup.a
print(a_tag.find_next_sibling('a'))
print(a_tag.find_next_siblings('a'))

3.find_previous_siblings() find_previous_sibling find_all_next() find_next()

find_previous_siblings() 往上搜索所有兄弟
find_previous_sibling() 往上搜索单个兄弟
find_all_next() 往下搜索所有元素
find_next()往下查找单个元素

a_tag=soup.find(id='link3')
# print(a_tag)
# print(a_tag.find_previous_sibling())
# print(a_tag.find_previous_siblings())
p_tag=soup.p
print(p_tag.find_all_next())
print(p_tag.find_next('a'))

# 爬取全国所有的城市名称以及对应的气温
import requests
from bs4 import BeautifulSoup
def parse_page(url):
    response=requests.get(url)
    text=response.content.decode('utf-8')
    soup=BeautifulSoup(text,'html5lib')
    conMidtab=soup.find('div',class_='conMidtab')
    # print('conMidtab')
    tables=conMidtab.find_all('table')
    for table in tables:
        trs=table.find_all('tr')[2:]
        for index,tr in enumerate(trs):
            tds=tr.find_all('td')
            city_td=tds[0]
            if index==0:
                city_td=tds[1]
            city=list(city_td.stripped_strings)[0]
            temp_td=tds[-2]
            temp=list(temp_td.stripped_strings)[0]
            print('城市：',city,'温度：',temp)


def main():
    #url = 'http://www.weather.com.cn/textFC/hb.shtml'  # 华东
    # url = 'http://www.weather.com.cn/textFC/db.shtml' # 东北
    #url = 'http://www.weather.com.cn/textFC/gat.shtml'  # 港澳台
    urls = ['http://www.weather.com.cn/textFC/hb.shtml', 'http://www.weather.com.cn/textFC/db.shtml',
            'http://www.weather.com.cn/textFC/gat.shtml']
    for url in urls:
        parse_page(url)
if __name__ == '__main__':
    main( )