Python学习笔记-第十六天

** 爬取糗百的段子 **
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import url_lib
import urllib2
import re

page = 1
url = 'http://www.qiushibaike.com/hot/page/' + str(page)
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
headers = {'User-Agent': user_agent}
try:
    request = urllib2.Request(url, headers=headers)
    response = urllib2.urlopen(request)
    content = response.read().decode('utf-8')
    pattern = re.compile(
        '<div class="author clearfix">.*?href.*?<img src.*?title=.*?<h2>(.*?)</h2>.*?<div class="content">(.*?)</div>.*?<i class="number">(.*?)</i>', re.S)
    items = re.findall(pattern, content)
    for item in items:
        for it in item:
            print it.encode('utf-8')

except urllib2.URLError, e:
    if hasattr(e, 'code'):
        print e.code
    if hasattr(e, 'reason'):
        print e.reason

** 爬取猫眼榜单电影 **
import json
from multiprocessing import Pool
import requests
from requests.exceptions import RequestException
import re


def get_one_page(url):
    try:
        response = requests.get(url)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None


def parse_one_page(html):
    pattern = re.compile('<dd>.*?board-index.*?>(\d+)</i>.*?data-src="(.*?)".*?name"><a'
                         + '.*?>(.*?)</a>.*?star">(.*?)</p>.*?releasetime">(.*?)</p>'
                         + '.*?integer">(.*?)</i>.*?fraction">(.*?)</i>.*?</dd>', re.S)
    items = re.findall(pattern, html)
    for item in items:
        yield {
            'index': item[0],
            'image': item[1],
            'title': item[2],
            'actor': item[3].strip()[3:],
            'time': item[4].strip()[5:],
            'score': item[5] + item[6]
        }


def write_to_file(content):
    with open('result.txt', 'a', encoding='utf-8') as f:
        f.write(json.dumps(content, ensure_ascii=False) + '\n')
        f.close()


def main(offset):
    url = 'http://maoyan.com/board/4?offset=' + str(offset)
    html = get_one_page(url)
    for item in parse_one_page(html):
        print item['title'].encode('utf-8'), item['actor'].encode('utf-8'), item['score'].encode('utf-8'), item['time'].encode('utf-8')
        # write_to_file(item)


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