python学习之抓取博客园新闻

#! python3
# coding = utf-8
# get_cnblogs_news.py
# 根据博客园内的任意一篇新闻，获取所有新闻（标题、发布时间、发布人）
# 

# 这是标题格式 ：<div id="news_title"><a href="//news.cnblogs.com/n/570973/">SpaceX重复使用的“龙”飞船成功与国际空间站对接</a></div>
# 这是发布人格式 ：<span class="news_poster">投递人 <a href="//home.cnblogs.com/u/34358/">itwriter</a></span>
# 这是发布时间格式 ：<span class="time">发布于 2017-06-06 14:53</span>

# 当前新闻ID ：<input type="hidden" value="570981" id="lbContentID">

# html中获取不到上一篇和下一篇的直接链接，因为它是使用ajax请求后期渲染的
# 需要另外请求地址，获取结果，JSON
# 上一篇 
# 下一篇 

# 响应内容
# ContentID : 570971
# Title : "Mac支持外部GPU VR开发套件售599美元"
# Submitdate : "/Date(1425445514)"
# SubmitdateFormat : "2017-06-06 14:47"

import sys, pyperclip
import requests, bs4
import json

# 解析并打印（标题、作者、发布时间、当前ID）
# soup : 响应的HTML内容经过bs4转化的对象
def get_info(soup):
    dict_info = {'curr_id': '', 'author': '', 'time': '', 'title': '', 'url': ''}

    titles = soup.select('div#news_title > a')
    if len(titles) > 0:
        dict_info['title'] = titles[0].getText()
        dict_info['url'] = titles[0].get('href')

    authors = soup.select('span.news_poster > a')
    if len(authors) > 0:
        dict_info['author'] = authors[0].getText()

    times = soup.select('span.time')
    if len(times) > 0:
        dict_info['time'] = times[0].getText()

    content_ids = soup.select('input#lbContentID')
    if len(content_ids) > 0:
        dict_info['curr_id'] = content_ids[0].get('value')

    # 写文件
    with open('D:/cnblognews.csv', 'a') as f:
        text = '%s,%s,%s,%s\n' % (dict_info['curr_id'], (dict_info['author'] + dict_info['time']), dict_info['url'], dict_info['title'])
        print(text)
        f.write(text)
    return dict_info['curr_id']

# 获取前一篇文章信息
# curr_id : 新闻ID
# loop_count : 向上多少条，如果为0，则无限向上，直至结束
def get_prev_info(curr_id, loop_count = 0):
    private_loop_count = 0
    try:
        while loop_count == 0 or private_loop_count < loop_count:
            res_prev = requests.get('https://news.cnblogs.com/NewsAjax/GetPreNewsById?contentId=' + curr_id)
            res_prev.raise_for_status()
            res_prev_dict = json.loads(res_prev.text)
            prev_id = res_prev_dict['ContentID']

            res_prev = requests.get('https://news.cnblogs.com/n/%s/' % prev_id)
            res_prev.raise_for_status()
            soup_prev = bs4.BeautifulSoup(res_prev.text, 'html.parser')
            curr_id = get_info(soup_prev)

            private_loop_count += 1
    except:
        pass

# 获取下一篇文章信息
# curr_id : 新闻ID
# loop_count : 向下多少条，如果为0，则无限向下，直至结束
def get_next_info(curr_id, loop_count = 0):
    private_loop_count = 0
    try:
        while loop_count == 0 or private_loop_count < loop_count:
            res_next = requests.get('https://news.cnblogs.com/NewsAjax/GetNextNewsById?contentId=' + curr_id)
            res_next.raise_for_status()
            res_next_dict = json.loads(res_next.text)
            next_id = res_next_dict['ContentID']

            res_next = requests.get('https://news.cnblogs.com/n/%s/' % next_id)
            res_next.raise_for_status()
            soup_next = bs4.BeautifulSoup(res_next.text, 'html.parser')
            curr_id = get_info(soup_next)

            private_loop_count += 1
    except:
        pass


# 参数从优先从命令行获取，如果无，则从剪切板获取
# url是博客园新闻版块下，任何一篇新闻
if len(sys.argv) > 1:
    url = sys.argv[1]
else:
    url = pyperclip.paste()

# 没有获取到有地址，则抛出异常
if not url:
    raise ValueError

# 开始从源地址中获取新闻内容
res = requests.get(url)
res.raise_for_status()
if not res.text:
    raise ValueError

#解析Html
soup = bs4.BeautifulSoup(res.text, 'html.parser')
curr_id = get_info(soup)
print('backward...')
get_prev_info(curr_id)
print('forward...')
get_next_info(curr_id)
print('done')