本帖最后由 lifan1995 于 2022-11-6 11:56 编辑
新人第一次发帖，如有本人不了解的违规处，请管理员删帖
常年潜水，最近看到一些爬虫的分享，遂自己写了套代码练练手，与大家交流学习（python纯属自学），有什么代码建议请指出，谢谢大家
代码纯属学习
注意：
控制并发参数的设置：sem_pic，不要太大了，不要影响网站正常运行！！！
控制并发参数的设置：sem_pic，不要太大了，不要影响网站正常运行！！！
控制并发参数的设置：sem_pic，不要太大了，不要影响网站正常运行！！！
重要的事情说三遍
[Python] 纯文本查看 复制代码 import asyncio
import os
import re
import time
import aiohttp
from bs4 import BeautifulSoup
# 此处放绝对路径，此路径需要已存在
'''
实例：
linux：'/home/lifan/workspace/download/www.tuiimg.com/'
widows：'E:/picture/test'
'''
root_path = 'E:/picture/test'
url = 'https://www.tuiimg.com/meinv/'
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/107.0.0.0 Safari/537.36 Edg/107.0.1418.35",
'Pragma': 'no-cache',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
'Cache-Control': 'no-cache',
'Connection': 'keep-alive',
"Content-Type": "text/html;charset=utf-8"}
# 文件写入的并发限制
sem_write = asyncio.Semaphore(500)
# 请求分类页面的并发限制（不要一次请求太多分类）
sem_page = asyncio.Semaphore(10)
'''
单张图片有大有小，100-400kb之间
设置为5时，下载前2页内容，耗时182.47s，网速3-4m/s
设置为15时，下载前2页内容，耗时73.12s，网速7-9m/s
'''
# 请求图片的并发限制（主要考虑网站的带宽和自己的网速，下载速度和快慢主要取决于这个参数）
sem_pic = asyncio.Semaphore(15)
async def fetch_content(url):
'''
根据url获取内容
:param url: 网页的url
:return:
'''
async with sem_page:
print(f'开始解析链接：{url}')
max_retries = 3
attempt = 0
while True:
try:
async with aiohttp.ClientSession(
headers=headers, connector=aiohttp.TCPConnector(ssl=False)
) as session:
async with session.get(url, timeout=10) as resp:
return await resp.text()
break
except (
asyncio.TimeoutError
):
if attempt < max_retries:
print("解析链接异常，稍后自动重试：{} times:{}".format(url, attempt))
attempt += 1
else:
raise
async def write_pic(pic, img_path_name):
'''
写入图片
:param pic: 图片对象
:param img_path_name: 图片的路径
:return:
'''
async with sem_write:
with open(img_path_name, 'wb') as f:
f.write(pic)
print(f'写入图片：{img_path_name}')
async def download_one(img_url, img_path):
'''
下载一张图片
:param img_url: 图片的url
:param img_path: 图片存放的文件夹
:return:
'''
async with sem_pic:
img_name = img_url.split("/")[-1]
img_path_name = "{}/{}".format(img_path, img_name)
if not os.path.exists(img_path_name):
max_retries = 3
attempt = 0
while True:
try:
async with aiohttp.ClientSession(
headers=headers, connector=aiohttp.TCPConnector(ssl=False)
) as session:
async with session.get(img_url, timeout=10) as resp:
pic = await resp.read()
await write_pic(pic, img_path_name)
break
except (
asyncio.TimeoutError
):
if attempt < max_retries:
print("{}times:{}".format(img_path_name, attempt))
attempt += 1
else:
raise
async def page_pic(pic_page):
'''
处理一套图片，分文件夹存放
:param pic_page: 一套图片的url
:return:
'''
bs = BeautifulSoup(pic_page, 'lxml')
title = bs.find('title').get_text()
img_path = "{}/{}".format(root_path, "{}".format(title))
if not os.path.exists(img_path):
print(f'创建存放路径：{img_path}')
os.mkdir(img_path)
else:
print(f'已存在存放路径：{img_path}')
div = bs.find('div', {'class': "content"})
img_temp_link = div.find('img')['src']
img_base_link = img_temp_link[0:-5]
allText = bs.find('i', id='allbtn').get_text()
pattern = re.compile("\((.*?)\)")
total = pattern.search(allText).group(1).split("/")[1]
img_urls = []
for i in range(1, int(total) + 1):
img_url = img_base_link + str(i) + '.jpg'
img_urls.append(img_url)
task_img = [download_one(img_url, img_path) for img_url in img_urls]
await asyncio.gather(*task_img)
async def page_main(url):
'''
单页下载
:param url: 单页的url
:return: None
'''
mainPageText = await fetch_content(url)
bs = BeautifulSoup(mainPageText, 'lxml')
a_all = bs.find_all('a', {'class': 'pic'})
page_urls = []
for a in a_all:
page_urls.append(a['href'])
tasks = [fetch_content(pic_url) for pic_url in page_urls]
pic_pages = await asyncio.gather(*tasks)
pics = [page_pic(pic_page) for pic_page in pic_pages]
await asyncio.gather(*pics)
async def main():
'''
遍历所有页面的url进行下载
:return:
'''
await target_folder()
start = time.time()
mainPageText = await fetch_content(url)
bs = BeautifulSoup(mainPageText, 'lxml')
page_count = bs.find('div', {'class', 'page'}).find('a', {'class', "end"}).get_text()
page_urls = []
for i in range(1, int(page_count) + 1):
page_url = f'{url}list_{i}.html'
page_urls.append(page_url)
tasks = [page_main(page_url) for page_url in page_urls]
await asyncio.gather(*tasks)
end = time.time()
print(f"耗时：{end - start:.2f}秒")
async def target_folder():
'''
指定下载的目录，需要已存在的，此处特意没有自动创建
:return:
'''
if not os.path.exists(root_path):
raise Exception(f'指定的路径不存在：{root_path}')
if __name__ == '__main__':
# linux下用此方法
asyncio.run(main())
# windows下上面的方法会报错（会在运行完成后报错，不影响下载），可以换成用下面这两行
# loop = asyncio.get_event_loop()
# loop.run_until_complete(main())
| 
[复制链接]
发表于 2022-11-6 11:54
|
发表于 2022-11-13 15:06
