新手求助 - V2EX

一段代码，先获取一个网址的代码，再进行打印格式化，然后想通过进程池提高速度。用 pool=Pool(10),pool.map()这个代码实现，怎么实现啦。请大神帮帮忙。代码如下：
#!/usr/bin/python
#_*_ coding:utf8 _*_

import requests
from requests.excepti** import RequestException
import re

def get_one_page(url):
try:
resp**e = requests.get(url)
if resp**e.status_code == 200:
#print(resp**e.text)
#print(resp**e.encoding)
#print(resp**e.apparent_encoding)
#r = resp**e.text
#print(requests.utils.get_encodings_from_content(r)[0])
#a = r.encode('utf-8').decode(requests.utils.get_encodings_from_content(r)[0])
#print(a)
#print('------------------------------------')
#b = r.encode('utf-8').decode(resp**e.apparent_encoding)
#print(b)
return resp**e.text
return None
except RequestException:
return None

def parse_one_page(html):
pattern = re.compile('<li.*?cover.*?href="(.*?)".*?</li>',re.S)
result = re.findall(pattern,html)
print(result)

def main():
url = 'https://book.douban.com/'
html=get_one_page(url)
parse_one_page(html)

if __name__ == '__main__':
main()

这个后面的多进程怎么写，大神们帮帮忙。

resp

URL

HTML

4 replies

happykjoy

Sep 10, 2018

各位帮帮忙，我是小白

sunnyadamm

Sep 10, 2018

。。。你这代码贴的，估计大家连读都不想读。。。

happykjoy

Sep 10, 2018

#!/usr/bin/python
#_*_ coding:utf8 _*_

import requests
from requests.exceptions import RequestException
import re
from multiprocessing import Pool

def get_one_page(url):
try:
response = requests.get(url)
if response.status_code == 200:
#print(response.text)
#print(response.encoding)
#print(response.apparent_encoding)
#r = response.text
#print(requests.utils.get_encodings_from_content(r)[0])
#a = r.encode('utf-8').decode(requests.utils.get_encodings_from_content(r)[0])
#print(a)
#print('------------------------------------')
#b = r.encode('utf-8').decode(response.apparent_encoding)
#print(b)
return response.text
return None
except RequestException:
return None

def parse_one_page(html):
pattern = re.compile('<li.*?cover.*?href="(.*?)" title="(.*?)">.*?img src="(.*?)"'
'.*?author">(.*?)</div>.*?year">(.*?)</span>.*?publisher">(.*?)'
'</span>.*?abstract">(.*?)</p>.*?</li>',re.S)
result = re.findall(pattern,html)
for item in result:
yield {
'地址': item[0],
'书名': item[1],
'封面': item[2],
'作者': item[3].strip()[0:],
'出版时间': item[4].strip()[0:],
'出版社': item[5].strip()[0:],
'详细': item[6].strip()[0:]
}

def main():
url = 'https://book.douban.com/'
html=get_one_page(url)
for item in parse_one_page(html):
print(item)

if __name__=='__main__':
pool = Pool()
pool.map(main, [i * 10 for i in range(10)])
pool.close()
pool.join()

happykjoy

Sep 10, 2018

@sunnyadamm 抱歉，新手刚来，第一次贴代码，贴成纯文本格式了。