requests、bs4总结和作业-CFANZ编程社区

requests、bs4总结和作业

一、requests的用法

requests是Python用于网络(http)请求的第三库，也是爬虫获取网络数据的重要工具

1. 向目标地址(网络地址)发送请求
requests.get(url,*,headers, proxies, timeout)   -  以指定的方式给地址发送网络请求，返回值是服务器返回的响应对象

参数说明：
url  -  字符串；请求的网络地址，可能是目标网站的网址也可能是数据接口
headers  -  字典；请求头，用于伪装浏览器设置user-agent、完成自动登录设置cookie
proxies  -  字典；设置代理ip(ip地址被封的时候使用)
timeout  -  数字；设置超时时间

url = 'https://search.51job.com/list/000000,000000,0000,00,9,99,数据分析,2,1.html?lang=c&postchannel=0000&workyear=99&cotype=99&degreefrom=99&jobterm=99&companysize=99&ord_field=0&dibiaoid=0&line=&welfare='
headers = {
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36'
}
response = requests.get(url, headers=headers)

#2. 获取响应头
print(response.headers)

#3. 设置响应的编码方式(在获取请求结果乱码的时候使用)
response.encoding = 'gbk'

# 4.获取请求结果
# 1）获取字符串格式的结果(爬网页)
print(response.text)

# 2) 获取二进制格式的结果(爬图片、视频、音频)
print(response.content)

# 3)获取json解析的结果(爬接口数据)
print(response.json())

二、爬网页

import requests

url = 'https://cd.zu.ke.com/zufang'
response = requests.get(url)
print(response.text)

三、下载图片

import requests

# 1. 对图片地址发送请求
url = 'https://www.baidu.com/img/PCtm_d9c8750bed0b3c7d089fa7d55720d6cf.png'
response = requests.get(url)

# 2. 保存图片数据到本地
open('files/a.png', 'wb').write(response.content)

四、json接口数据

import requests
import os

url = 'https://game.gtimg.cn/images/lol/act/img/js/heroList/hero_list.js'
response = requests.get(url)

count = 0
for hero in response.json()['hero']:
    print(hero['name'])
    a_url = hero['selectAudio']
    res = requests.get(a_url)
    open(f'files/{os.path.basename(a_url)}', 'bw').write(res.content)
    count += 1
    if count == 10:
        break

五、bs4的用法

from bs4 import BeautifulSoup
注意：安装第三方库的时候安装beautifulSoup4而不是bs4

#1. 创建BeautifulSoup对象
#BeautifulSoup(html代码, 'lxml')   -  返回网页对象
html = open('files/05css选择器(重要).html',encoding='utf-8').read()
soup = BeautifulSoup(html, 'lxml')

# 2. 获取标签
# 1) 基于整个网页获取标签
# BeautifulSoup对象.select(css选择器)   -   返回css选择器在整个网页中选中的所有标签；返回值是列表，列表中元素是标签对象
# BeautifulSoup对象.select_one(css选择器)  -  返回css选择器在整个网页中选中的第一个标签，返回值是标签对象
result = soup.select('p')
print(result)

result = soup.select('.c1')
print(result)

# 2）基于指定标签获取标签
# 标签对象.select(css选择器)   -   在指定标签中按照选择器选中相关标签
# 标签对象.select_one(css选择器)
div1 = soup.select_one('#box')
result = div1.select('p')
print(result)

# 3.获取标签内容和标签属性值
# 1)获取标签内容：
# 标签对象.text
result = soup.select_one('#p2').text
print(result)   # 我是段落2

# 获取所有p标签的标签内容
for p in soup.select('p'):
    print(p.text)

# 2)获取标签属性
# 标签对象.attrs[属性名]
result = soup.select_one('#a1').attrs
print(result)       # {'id': 'a1', 'href': 'https://www.baidu.com'}
result = soup.select_one('#a1').attrs['href']
print(result)       # 'https://www.baidu.com'

作业

#爬取豆瓣排名前250的电影信息
import requests
from bs4 import BeautifulSoup
from re import search
import csv
import time


def get_one_page(page):
    headers = {
        'cookie': 'bid=g16urOELfcQ; douban-fav-remind=1; __gads=ID=3f57e16f48f82cf2-2222dd78d6d0003d:T=1646561716:RT=1646561716:S=ALNI_MZc-Jdw3ejofw4l88N8mdU7MdYYzg; ll="118318"; __utma=30149280.808328653.1646561718.1646561718.1646561718.1; __utmz=30149280.1646561718.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none); ct=y; dbcl2="222590700:fEe+R6RmPAA"; ck=4rf3; push_noty_num=0; push_doumail_num=0',
        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36'
    }
    url = f'https://movie.douban.com/top250?start={page * 25}&amp;filter='
    response = requests.get(url, headers=headers)
    soup = BeautifulSoup(response.text, 'lxml')
    all_li = soup.select('.grid_view>li')
    all_data = []
    for li in all_li:
        # 电影名
        name = li.select_one('.title').text
        result = li.select_one('.bd>p').text.strip().replace(' ', '')
        # print('==============================================')
        # print(result)
        # 导演
        director = search(r'导演:(.+?)\s', result).group(1)
        # 主演
        actor = search(r'主演:(.+?)\s', result)
        if actor:
            actor = actor.group(1)

        # 上映时间
        time = search(r'\n(\d+).*?/', result).group(1)
        # 国家
        country = search(r'\n.+?/\s*(.+?)\s*/', result).group(1)
        # print(country)
        # 类型
        type = search(r'/.+?/\s*(.+?)$', result).group(1)
        # print(type)
        # 评分
        score = li.select_one('.rating_num').text
        # 人数
        comment_num = li.select('.star>span')[-1].text
        comment_num = search(r'\d+', comment_num).group()
        # 图片地址
        img_url = li.select_one('.pic img').attrs['src']

        # 保存数据
        all_data.append([name, director, actor, time, country, type, score, comment_num, img_url])

    writer = csv.writer(open('files/电影.csv', 'a', encoding='utf-8', newline=''))
    if page == 0:
        writer.writerow(['电影名称', '导演', '主演', '上映时间', '国家', '类型', '评分', '评论人数', '封面地址'])
    writer.writerows(all_data)
    print(f'==========第{page+1}页获取成功===========')


if __name__ == '__main__':
    for page in range(10):
        get_one_page(page)
        time.sleep(1)