From 1f6ddc35ba99a0dd4f5dea1a51a7ca6019aafba1 Mon Sep 17 00:00:00 2001
From: aiguigu <aiyingfeng110@qq.com>
Date: Mon, 20 Dec 2021 01:59:13 +0800
Subject: [PATCH] =?UTF-8?q?=E4=BF=AE=E5=A4=8D=E4=BB=A3=E7=A0=81?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 1688/spider/图片下载多线程.py | 56 +++++++++++++++++++++++++++++++++++
 1 file changed, 56 insertions(+)
 create mode 100644 1688/spider/图片下载多线程.py

diff --git a/1688/spider/图片下载多线程.py b/1688/spider/图片下载多线程.py
new file mode 100644
index 0000000..8a73ec2
--- /dev/null
+++ b/1688/spider/图片下载多线程.py
@@ -0,0 +1,56 @@
+from lxml import etree
+from time import time
+import asyncio
+import aiohttp
+
+url = 'https://movie.douban.com/top250'
+
+
+async def fetch_content(url):
+    async with aiohttp.ClientSession() as session:
+        async with session.get(url) as response:
+            return await response.text()
+
+
+async def parse(url):
+    page = await fetch_content(url)
+    html = etree.HTML(page)
+
+    xpath_movie = '//*[@id="content"]/div/div[1]/ol/li'
+    xpath_title = './/span[@class="title"]'
+    xpath_pages = '//*[@id="content"]/div/div[1]/div[2]/a'
+
+    pages = html.xpath(xpath_pages)
+    fetch_list = []
+    result = []
+
+    for element_movie in html.xpath(xpath_movie):
+        result.append(element_movie)
+
+    for p in pages:
+        fetch_list.append(url + p.get('href'))
+
+    tasks = [fetch_content(url) for url in fetch_list]
+    pages = await asyncio.gather(*tasks)
+
+    for page in pages:
+        html = etree.HTML(page)
+        for element_movie in html.xpath(xpath_movie):
+            result.append(element_movie)
+
+    for i, movie in enumerate(result, 1):
+        title = movie.find(xpath_title).text
+        print(i, title)
+
+
+def main():
+    loop = asyncio.get_event_loop()
+    start = time()
+    for i in range(5):
+        loop.run_until_complete(parse(url))
+    end = time()
+    print('Cost {} seconds'.format((end - start) / 5))
+    loop.close()
+
+
+main()