单个图片获取-爬取网易"数读"信息数据(暴涨的房租，正在摧毁中国年轻人的生活)

参考链接:https://www.makcyun.top/web_scraping_withpython3.html

该网页其实有16张图片,但是因为页面数据中某处多个空白,导致参考链接中的方式只有15张图片,并且亲测有些方式能用,有些方式不能用,特此记录一下

正常显示:

不正常显示:

 

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import random
import re

import requests
from bs4 import BeautifulSoup
from lxml import etree
from pyquery import PyQuery as pq
from requests import RequestException

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:60.0) Gecko/20100101 Firefox/60.0'
}


def get_one_page():
    url = 'http://data.163.com/18/0901/01/DQJ3D0D9000181IU.html'
    try:
        response = requests.get(url, headers=headers)
        if response.status_code == 200:
            return response.text
    except RequestException:
        print('网页请求失败')
        return None


### 如下是解析网页数据的5中方式

# 正则表达式
def parse_one_page1(html):
    pattern = re.compile('<img alt=".*?租" src="(.*?)"', re.S)
    items = re.findall(pattern, html)
    for item in items:
        yield {
            'url': item
        }


# Xpath语法 # 使用这个('*//p//img[@alt = "房租"]/@src') 则结果只有15条,因为有个alt参数中房租前面有空格
def parse_one_page2(html):
    parse = etree.HTML(html)
    items = parse.xpath('*//img[@style="margin: 0px auto; display: block;" ]/@src')
    for item in items:
        yield {
            'url': item
        }


# CSS选择器,结果有8条,还有待研究
def parse_one_page3(html):
    soup = BeautifulSoup(html, 'lxml')
    items = soup.select('p a img')
    # print(items)
    for item in items:
        yield {
            'url': item['src']
        }


# Beautiful Soup + find_all函数提取 结果有8条,还有待研究
def parse_one_page4(html):
    soup = BeautifulSoup(html, 'lxml')
    item = soup.find_all(attrs={'width': '100%', 'style': 'margin: 0px auto; display: block;'})
    print(item)
    for i in range(len(item)):
        url = item[i].attrs['src']
        yield {
            'url': url
        }


# PyQuery
def parse_one_page5(html):
    data = pq(html)
    data2 = data('p>a>img')
    for item in data2.items():
        yield {
            'url': item.attr('src')
        }


def download_thumb(url, name):
    print(url, name)
    try:
        response = requests.get(url)
        with open(name + '.jpg', 'wb') as f:
            f.write(response.content)
    except RequestException as e:
        print(e)
        pass


def main():
    html = get_one_page()
    items = parse_one_page5(html)
    for item in items:
        # print(item['url'])
        download_thumb(item['url'], str(random.randint(1, 1000)))


if __name__ == '__main__':
    main()

注:下载保存图片的函数还能再优化一下,不过懒得弄了,直接上随机数,哈哈