** 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()
