爬虫：Python爬取煎蛋网图片

学以致用

说明

我们学习python这么久，是时候拿它来做些什么了：

1. 爬虫 ，爬取网页图片；
2. 本代码仅供大量的互联网朋友们参考学习，欢迎交流；

图片

图片: 下面是我们下载下来的部分截图

代码展示

下面是我们的所有代码 代码片.

'''
    Author:Dew
    Time:2020/06/12 18:39
    Content:爬取煎蛋网的图片(Crawl pictures of omelette)
'''
from bs4 import BeautifulSoup
import urllib.request
from urllib.request import urlretrieve
import requests
import os
import time
import re
import lxml
import random

i = 0
if __name__ == '__main__':
    list_url = []
    for num in range(127, 132):
        if num == 1:
            url = 'http://jandan.net/ooxx'
        else:
            url = 'http://jandan.net/ooxx/MjAyMDA2MTItMTI%d#comments' % (num-124)
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36"
        }
        req = requests.get(url=url, headers=headers)
        req.encoding = 'utf-8'
        html = req.text
        # print(html)
        bf = BeautifulSoup(html, 'lxml')
        targets_url = bf.find_all(class_='view_img_link')

        for each in targets_url:
            list_url.append('http://' + each.get('href').replace('//', ''))

    print(list_url)
    os.makedirs('images')
    os.chdir('images')

    for target_url in list_url:

        filename = ' ' + str(time.localtime()) + '.jpg'

        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36"
        }
        response = urllib.request.urlopen(url=target_url)

        # img_req = requests.get(url=target_url, headers=headers)
        img = response.read()
        # img_req.encoding = 'utf-8'
        # img_html = img_req.text
        # img_bf = BeautifulSoup(img_html, 'lxml')
        # print(img)
        # c = random(0,200)
        # print(c)
        # if 'images2' not in os.listdir():

        i += 1
        # urlretrieve(url = target_url, filename=('images/' + filename))
        with open('images%s.jpg' %i, 'wb') as f:
            f.write(img)
            f.close()

        time.sleep(1)

    print('下载完成！')