Python Day2 爬虫基础操作【初级】

Day2 爬虫

1. 图片下载

import requests


def download_image(url:str):
    # 1.请求网页
    response = requests.get(url)

    # 2.获取图片数据
    data = response.content

    # 3.将数据写入图片文件中
    with open('懒洋洋.jpeg', 'wb') as f:
        f.write(data)

if __name__ == '__main__':
    download_image('https://cn.bing.com/search?q=%E6%87%92%E6%B4%8B%E6%B4%8B%E5%9B%BE%E7%89%87&form=ANNTH1&refig=7ab020bb977b49d59ac43bb4bd63b09b&sp=2&qs=SC&pq=%E6%87%92%E6%B4%8B%E6%B4%8B&sk=SC1&sc=10-3&cvid=7ab020bb977b49d59ac43bb4bd63b09b')

2. 网站批量下载图片

import requests
from re import findall
from uuid import uuid1   #  可以创建唯一的一个id值


def download_image(url: str):
    response = requests.get(url)
    with open(f'{uuid1()}.jpeg', 'wb') as f:
        f.write(response.content)


# 1.请求网页
response = requests.get('http://cd.zu.ke.com/zufang')
content = response.text
# print(content)

# 2.解析数据获取所有房屋的图片地址
all_images = findall(r'(?s)<a\s+class="content__list--item--aside".+?>\s+<img.+/data-src="(.+?)"', content)

# 3.下载所有图片：
for i in all_images:
    download_image(i)

3. 浏览器伪装

import requests

Headers = {
    'User_Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.81 Safari/537.36 Edg/104.0.1293.47'
}

response = requests.get('https://movie.douban.com/top250', headers=Headers)

print(response.status_code)
print(response.text)

4. bs4数据解析

4.1 bs4的作用

专门用来解析网页数据的第三方库。（基于css选择器解析网页数据）
这个库下载的时候用’beautifulsoup4’， 使用的时候用’bs4’

注意：在使用bs4做数据解析的时候，需要依赖’lxml’这个第三方库

导入解析相关类

from bs4 import BeautifulSoup

4.2 bs4的用法

1）准备需要解析的数据（获取网页数据）

html = open('text.html', encoding='utf-8').read()

2）基于网页源代码，创建BeautifulSoup对象
soup对象代表网页对于的HTML标签（代表整个网页）

soup = BeautifulSoup(html, 'lxml')

3）获取标签
soup.select(css选择器) - soup代表的是整个网页，在整个网页中获取css选择器选中的所有标签，返回值是一个列表，列表中的元素是标签对象
soup.select_one(css选择器) - 在整个网页中获取css选择器选中的第一个标签，返回值是标签对象

result = soup.select('#box1 p')
print(result)       # [<p>肖生克的救赎</p>, <p>霸王别姬</p>, <p>阿甘正传</p>]

result = soup.select_one('#box1 p')
print(result)       # <p>肖生克的救赎</p>

标签对象.select(css选择器) - 在指定标签中获取css选择器选中的所有表情，返回值是一个列表，列表中元素是标签对象
标签对象.select_one(css选择器) - 在指定标签中获取css选择器选中的第一个标签，返回值是标签对象

result = soup.select('p')
print(result)       # [<p>肖生克的救赎</p>, <p>霸王别姬</p>, <p>阿甘正传</p>, <p>我是段落1</p>]

box2 = soup.select_one('#box2')
result = box2.select('p')
print(result)       # [<p>我是段落1</p>]

4)获取标签内容和标签属性

p = soup.select_one('p')            #  <p>肖生克的救赎</p>
img = soup.select_one('img')

a. 获取标签内容: 标签对象.text

print(p.text)       # '肖生克的救赎'

b.获取标签属性值: 标签对象.attrs[属性名]

print(img.attrs['src'], img.attrs['alt'])

5. bs4解析某瓣电影单页数据

import requests
from bs4 import BeautifulSoup
import csv


# 1.请求网页
def get_net_data(url: str):
    Headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.81 Safari/537.36 Edg/104.0.1293.47'
    }
    response = requests.get(url, headers=Headers)
    print(response.status_code)
    return response.text


# 2.网页数据解析
def analysis_data(html: str):
    soup = BeautifulSoup(html, 'lxml')
    all_film_div = soup.select('grid_view>li>.item')
    all_data = []
    for div in all_film_div:
        name = div.select_one('.title').text
        info = div.select_one('.bd>p').text.strip().split('\n')[-1].strip()
        time, country, category = info.split('/')
        score = div.select_one('.rating_num').text
        comment_count = div.select('.star>span')[-1].text[:-3]
        intro = div.select_one('.inq').text
        all_data.append([name, score, time.strip(), country.strip(), category.strip(), comment_count, intro])

    # 保存数据
    f = open('第一页电影数据.csv', 'w', encoding='utf-8', newline='')
    writer = csv.writer(f)
    writer.writerow(['电影名', '评分', '上映时间', '国家', '类型', '评论数', '简介'])
    writer.writerows(all_data)


if __name__ == '__main__':
    result = get_net_data('https://movie.douban.com/top250')
    analysis_data(result)

6. bs4解析某瓣电影十页数据

import requests
from bs4 import BeautifulSoup
import csv


# 1. 获取网页数据
def get_net_data(url: str):
    headers = {
        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36'
    }
    response = requests.get(url, headers=headers)
    return response.text


# 2. 网页数据解析
def analysis_data(html: str):
    # 解析数据
    soup = BeautifulSoup(html, 'lxml')
    all_film_div = soup.select('.grid_view>li>.item')
    all_data = []
    for div in all_film_div:
        name = div.select_one('.title').text
        info = div.select_one('.bd>p').text.strip().split('\n')[-1].strip()
        # time, country, category = info.split('/')
        info_list = info.split('/')
        time = info_list[0]
        country = info_list[-2]
        category = info_list[-1]
        score = div.select_one('.rating_num').text
        comment_count = div.select('.star>span')[-1].text[:-3]
        intro_span = div.select_one('.inq')
        if intro_span:
            intro = intro_span.text
        else:
            intro = ''
        all_data.append([name, score, time.strip(), country.strip(), category.strip(), comment_count, intro])

    writer.writerows(all_data)
    print('保存成功！')


if __name__ == '__main__':
    f = open('豆瓣电影.csv', 'w', encoding='utf-8', newline='')
    writer = csv.writer(f)
    writer.writerow(['电影名', '评分', '上映时间', '国家', '类型', '评论数', '简介'])

    for page in range(0, 251, 25):
        url = f'https://movie.douban.com/top250?start={page}&filter='
        result = get_net_data(url)
        analysis_data(result)