Python今日头条网爬虫

encoding=utf8

import requests
from requests.exceptions import RequestException
import urllib
import json
import re
from bs4 import BeautifulSoup
from config import *
def get_index(offset,keyword):
data={
'offset':offset,
'format':'json',
'keyword':keyword,
'autoload':'true',
'count':20,
'cur_tab':3
}
url='http://www.toutiao.com/search_content/?'+urllib.urlencode(data)
response=requests.get(url)
try:
if response.status_code == 200:
return response.text
return None
except RequestException:
print u'请求索引页出错'
return None
def parse_page_index(html):
#将json格式的字符串转化成python对象，对象转换成json用 json.dumps()
data=json.loads(html)
if data and 'data' in data.keys():
for item in data.get('data'):
#yield 是url生成器 即取出article_url并生成url
yield item.get('article_url')
def get_page_detail(url):
response = requests.get(url)
try:
if response.status_code == 200:
return response.text
return None
except RequestException:
print '请求详情页出错'
return None
def parse_page_detail(html,url):
soup=BeautifulSoup(html,'lxml')
title = soup.select('title')[0].get_text()
images_pattern= re.compile('var gallery = (.*?);',re.S)
result = re.search(images_pattern,html)
if result:
data =json.loads(result.group(1))
sub_images = data.get('sub_images')
images = [item.get('url') for item in sub_images]
return {
'title' :title,
'url':url,
'images':images
}
def main():
html=get_index(0,'街拍')
for url in parse_page_index(html):
html=get_page_detail(url)
if html:
result=parse_page_detail(html,url)
print result['title']
if name == 'main':
main()