爬虫DAY7

最新推荐文章于 2022-03-14 20:19:57 发布

wssssang

最新推荐文章于 2022-03-14 20:19:57 发布

阅读量85

点赞数

分类专栏： python 爬虫

本文链接：https://blog.csdn.net/weixin_47798560/article/details/110498774

版权

python 同时被 2 个专栏收录

34 篇文章 5 订阅

订阅专栏

爬虫

8 篇文章 0 订阅

订阅专栏

beautifulsoup

#coding = utf-8
from  bs4 import BeautifulSoup

html_doc = """
<html><head><title id = "one">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>
"""

#1.转类型
#默认bs4会  调用你系统中lxml的解析库  警告提示
#主动设置  bs4的解析库
soup = BeautifulSoup(html_doc,'lxml')

#2.通用解析方法

#find--返回符合查询条件的  第一个标签
#result = soup.find(name = "a")
#result = soup.find(attrs={"class":"title"})
#result = soup.find(text="Tillie")
result = soup.find(
    name = 'p',
    attrs={"class":"story"}
)

#find_all--list(标签对象)
result= soup.find_all('a')
result= soup.find_all("a",limit=1)
result = soup.find_all(attrs={"class":"sister"})

#selcet_one---css选择器
result = soup.select_one('.sister')

#select---css选择器
#.info---class选择器，匹配所有class属性中包含info的元素
result = soup.select('.sister')
##footer---id选择器，匹配所有id属性等于footer的元素
result = soup.select('#one')
#后代选择器
result = soup.select('head title')
result = soup.select('title,.title')
result = soup.select('a[id = "link3"]')

#标签包裹的内容---list
result = soup.select('b')[0].get_text()

#标签的属性
result = soup.select('#link1')[0].get('href')
print(result)

用bs爬取btc网站

import requests
from bs4 import BeautifulSoup
from lxml import etree
import json


class BtcSpider(object):
    def __init__(self):
        self.url = 'http://8btc.com/forum-61-{}.html'
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36"}

        # 保存列表页的数据
        self.data_list = []

        self.data_detail = []

    # 1.发请求
    def get_response(self, url):
        response = requests.get(url, headers=self.headers)
        data = response.content
        return data

    # 2.解析数据list
    def parse_list_data(self, data):

        # 1.转类型
        soup = BeautifulSoup(data, 'lxml')
        # 2.解析内容 取出 所有的类选择器的 A
        title_list = soup.select('.xst')
        for title in title_list:
            list_dict_data = {}
            list_dict_data['title'] = title.get_text()
            list_dict_data['detail_url'] = title.get('href')
            self.data_list.append(list_dict_data)

    # 3.解析数据详情页
    def parse_detail_data(self, data):
        html_data = BeautifulSoup(data, 'lxml')

        # 取出问题--list[1][0]
        question = html_data.select('#thread_subject')[0].get_text()
        print(question)
        answer_list = html_data.select('.t_f')
        for answer in answer_list:
            answer_list = []
            answer_list.append(answer.get_text())

        detail_data = {
            "question": question,
            "answer": answer_list
        }

        self.data_detail.append(detail_data)

    # 3.保存数据
    def save_data(self, data, file_path):
        data_str = json.dumps(data)
        with open(file_path, 'w') as f:
            f.write(data_str)

    def start(self):
        # 列表页的请求
        for i in range(1, 2):
            url = self.url.format(1)
            data = self.get_response(url)
            self.parse_list_data(data)
        self.save_data(self.data_list, "04list.json")

        # 发送详情页的请求
        for data in self.data_list:
            detail_url = data['detail_url']
            detail_data = self.get_response(detail_url)

            # 解析详情页的数据
            self.parse_detail_data(detail_data)

        self.save_data(self.data_detail, 'detail.json')


BtcSpider().start()

"""
html_data = etree.HTML(data)

        result_list = html_data.xpath('//div[contains(@id,"stickthread")]')
        result_list = html_data.xpath('//head/following-sibling::*[1]')
        print(len(result_list))
        print(result_list)
"""

wssssang

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
爬虫DAY7

beautifulsoup#coding = utf-8from bs4 import BeautifulSouphtml_doc = """<html><head><title id = "one">The Dormouse's story</title></head><body><p class="title"><b>The Dormouse's story</b></p&g
复制链接

扫一扫

专栏目录