# 引入相關(guān)第三方庫(kù)，requests負(fù)責(zé)網(wǎng)絡(luò)請(qǐng)求，BeautifulSoup負(fù)責(zé)html解析，wget的download負(fù)責(zé)下載
import requests
from bs4 import BeautifulSoup
from wget import download
# 從瀏覽器F12的‘network’中獲取User-Agent作為headers，以偽裝成瀏覽器，保持爬蟲(chóng)穩(wěn)定性(參考get-headers.png)。
headers = {'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko)'
' Chrome/86.0.4240.198 Safari/537.36 Edg/86.0.622.69'}
# 指定網(wǎng)址
url = r"https://bj.xiaozhu.com/"
# 獲取網(wǎng)頁(yè)html
web_data = requests.get(url, headers=headers).text
# 使用python自帶的html.parser或者lxml來(lái)解析html
bs = BeautifulSoup(web_data, 'html.parser')
# 使用BeautifulSoup的選擇器來(lái)獲取指定的標(biāo)簽，返回的是Tag類型的ResultSet
imgs = bs.select('#page_list > ul > li:nth-child(1) > a > img')
# 遍歷ResultSet，根據(jù)標(biāo)簽屬性名獲取屬性內(nèi)容，最后使用wget的download下載指定url對(duì)應(yīng)的圖片
for img in imgs:
download(img.get('lazy_src'))
------------------------------------------------------------------------------------------- by Silence @ 2020/11/19 -----------
