'''
同步方式爬取當(dāng)當(dāng)暢銷書的圖書信息
'''
import time
import requests
import pandas as pd
from bs4 import BeautifulSoup
# table表格用于儲(chǔ)存書本信息
table = []
# 處理網(wǎng)頁(yè)
def download(url):
html = requests.get(url).text
# 利用BeautifulSoup將獲取到的文本解析成HTML
soup = BeautifulSoup(html, "lxml")
# 獲取網(wǎng)頁(yè)中的暢銷書信息
book_list = soup.find('ul', class_="bang_list clearfix bang_list_mode")('li')
for book in book_list:
info = book.find_all('div')
# 獲取每本暢銷書的排名，名稱，評(píng)論數(shù)，作者，出版社
rank = info[0].text[0:-1]
name = info[2].text
comments = info[3].text.split('條')[0]
author = info[4].text
date_and_publisher = info[5].text.split()
publisher = date_and_publisher[1] if len(date_and_publisher) >= 2 else ''
# 將每本暢銷書的上述信息加入到table中
table.append([rank, name, comments, author, publisher])
# 全部網(wǎng)頁(yè)
urls = ['http://bang.dangdang.com/books/bestsellers/01.00.00.00.00.00-recent7-0-0-1-%d' % i for i in range(1, 26)]
# 統(tǒng)計(jì)該爬蟲的消耗時(shí)間
print('#' * 50)
t1 = time.time() # 開(kāi)始時(shí)間
for url in urls:
download(url)
# 將table轉(zhuǎn)化為pandas中的DataFrame并保存為CSV格式的文件
df = pd.DataFrame(table, columns=['rank', 'name', 'comments', 'author', 'publisher'])
df.to_csv('E://douban/dangdang.csv', index=False)
t2 = time.time() # 結(jié)束時(shí)間
print('使用一般方法，總共耗時(shí)：%s' % (t2 - t1))
print('#' * 50)

'''
異步方式爬取當(dāng)當(dāng)暢銷書的圖書信息
'''
import time
import aiohttp
import asyncio
import pandas as pd
from bs4 import BeautifulSoup
# table表格用于儲(chǔ)存書本信息
table = []
# 獲取網(wǎng)頁(yè)（文本信息）
async def fetch(session, url):
async with session.get(url) as response:
return await response.text(encoding='gb18030')
# 解析網(wǎng)頁(yè)
async def parser(html):
# 利用BeautifulSoup將獲取到的文本解析成HTML
soup = BeautifulSoup(html, "lxml")
# 獲取網(wǎng)頁(yè)中的暢銷書信息
book_list = soup.find('ul', class_="bang_list clearfix bang_list_mode")('li')
for book in book_list:
info = book.find_all('div')
# 獲取每本暢銷書的排名，名稱，評(píng)論數(shù)，作者，出版社
rank = info[0].text[0:-1]
name = info[2].text
comments = info[3].text.split('條')[0]
author = info[4].text
date_and_publisher = info[5].text.split()
publisher = date_and_publisher[1] if len(date_and_publisher) >=2 else ''
# 將每本暢銷書的上述信息加入到table中
table.append([rank,name,comments,author,publisher])
# 處理網(wǎng)頁(yè)
async def download(url):
async with aiohttp.ClientSession() as session:
html = await fetch(session, url)
await parser(html)
# 全部網(wǎng)頁(yè)
urls = ['http://bang.dangdang.com/books/bestsellers/01.00.00.00.00.00-recent7-0-0-1-%d'%i for i in range(1,26)]
# 統(tǒng)計(jì)該爬蟲的消耗時(shí)間
print('#' * 50)
t1 = time.time() # 開(kāi)始時(shí)間
# 利用asyncio模塊進(jìn)行異步IO處理
loop = asyncio.get_event_loop()
tasks = [asyncio.ensure_future(download(url)) for url in urls]
tasks = asyncio.gather(*tasks)
loop.run_until_complete(tasks)
# 將table轉(zhuǎn)化為pandas中的DataFrame并保存為CSV格式的文件
df = pd.DataFrame(table, columns=['rank','name','comments','author','publisher'])
df.to_csv('E://douban/dangdang.csv',index=False)
t2 = time.time() # 結(jié)束時(shí)間
print('使用aiohttp，總共耗時(shí)：%s' % (t2 - t1))
print('#' * 50)