bs4实战

最新推荐文章于 2023-01-02 12:13:40 发布

intmain_S

最新推荐文章于 2023-01-02 12:13:40 发布

阅读量307

点赞数

分类专栏：爬虫文章标签： python

本文链接：https://blog.csdn.net/intmain_S/article/details/123742917

版权

爬虫专栏收录该内容

6 篇文章 0 订阅

订阅专栏

import csv
import time

import requests
from bs4 import BeautifulSoup

# url = 'https://movie.douban.com/top250'
# headers = {
#     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.74 Safari/537.36'
# }
#
# resp = requests.get(url=url, headers=headers)
# print(resp.text)
# page = BeautifulSoup(resp.text, 'html.parser')
# table = page.find('table', attrs={'class': 'hq_table'})
#
# trs = table.find_all("tr")[1:]
# f = open('a.csv', mode='w', encoding='utf-8')
# writer = csv.writer(f)
# for i in trs:
#     tds = i.find_all('td')
#     n1 = tds[0].txt
#     n2 = tds[1].txt
#     writer.writerow([n1, n2])
url = 'https://www.53pic.com/bizhi/weimei/'

domain = 'https://www.53pic.com'

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.51 Safari/537.36'
}

resp = requests.get(url=url, headers=headers)
resp.encoding = 'utf-8'
# print(resp.text)

page = BeautifulSoup(resp.text, 'html.parser')
div = page.find('div', attrs={'class': 'work-list-box'}).find_all('a', attrs={'class': 'card-img-hover'})

# print(div)
# link_list = []


for i in div:
    # 拿到子页面源代码
    target = domain + i.get('href')
    #     link_list.append(target)
    #     print(target)
    # print(link_list)
    child_page_resp = requests.get(target)
    child_page_resp.encoding = 'utf-8'
    page2 = BeautifulSoup(child_page_resp.text, 'html.parser')
    # 拿到子页面图片地址
    img = page2.find('img')
    img_src = img.get('src')
    # print(img_src)
    # 下载图片
    imp_resp = requests.get(img_src)

    img_name = img_src.split('/')[-1]
    with open(img_name, mode='wb') as f:  # 图片是字节形式存储的
        f.write(imp_resp.content)  # 图片写入文件
    print("over", img_name)
    time.sleep(1)  # 防止被服务器检查到

print("all over")
resp.close()