def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
source_url = url_info['url']
depth = url_info['depth']
website_id = url_info['site_id']
description = url_info['remark']
html = tools.get_html_by_urllib(source_url)
if html == None:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 判断中英文
regex = '[\u4e00-\u9fa5]+'
chinese_word = tools.get_info(html, regex)
if not chinese_word:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
urls = tools.get_urls(html)
fit_url = tools.fit_url(urls, FIT_URLS)
for url in fit_url:
# log.debug('url = ' + url)
base_parser.add_url('article_urls', website_id, url, depth + 1)
# 取当前页的文章信息
# 标题
regexs = '<h1.*?>(.*?)</h1>'
title = tools.get_info(html, regexs)
title = title and title[0] or ''
title = tools.del_html_tag(title)
# 内容
regexs = ['<div id="content">(.*?)<div class="clear"></div>',
'<div class="article">(.*?)<!--文章操作-->',
'<div id="video_area">(.*?)<!--文章操作-->',
'<div class="content">(.*?)<div id="article_edit">'
]
content = tools.get_info(html, regexs)
content = content and content[0] or ''
content = tools.del_html_tag(content)
log.debug('''
depth = %d
url = %s
title = %s
content = %s
'''%(depth+1, source_url, title, content))
if content and title:
base_parser.add_article_info('article_text_info', website_id, source_url, title, content)
# 更新source_url为done
base_parser.update_url('article_urls', source_url, Constance.DONE)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
source_url = url_info['url']
depth = url_info['depth']
website_id = url_info['site_id']
description = url_info['remark']
html = tools.get_html_by_urllib(source_url)
if html == None:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 判断中英文
regex = '[\u4e00-\u9fa5]+'
chinese_word = tools.get_info(html, regex)
if not chinese_word:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
urls = tools.get_urls(html, STOP_URLS)
urls = tools.fit_url(urls, "cctv.com")
for url in urls:
# log.debug('url = ' + url)
base_parser.add_url('article_urls', website_id, url, depth + 1)
# 取当前页的文章信息
# 标题
regexs = '<h1><!--repaste.title.begin-->(.*?)<!--repaste.title.end-->'
title = tools.get_info(html, regexs)
title = title and title[0] or ''
title = tools.del_html_tag(title)
# 内容
regexs = ['<!--repaste.body.begin-->(.*?)<!--repaste.body.end-->']
content = tools.get_info(html, regexs)
content = content and content[0] or ''
content = tools.del_html_tag(content)
log.debug('''
depth = %d
url = %s
title = %s
content = %s
''' % (depth + 1, source_url, title, content))
if content and title:
base_parser.add_article_info('article_text_info', website_id,
source_url, title, content)
# 更新source_url为done
base_parser.update_url('article_urls', source_url, Constance.DONE)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
source_url = url_info['url']
depth = url_info['depth']
website_id = url_info['site_id']
description = url_info['remark']
html = tools.get_html_by_urllib(source_url)
if html == None:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 判断中英文
regex = '[\u4e00-\u9fa5]+'
chinese_word = tools.get_info(html, regex)
if not chinese_word:
base_parser.update_url('article_urls', source_url, Constance.DONE)
return
# 取当前页面的全部url
urls = tools.get_urls(html, STOP_URLS)
# 过滤掉外链接 添加到数据库
fit_url = tools.fit_url(urls, "ifeng.com")
for url in fit_url:
# log.debug('url = ' + url)
base_parser.add_url('article_urls', url, website_id, depth + 1)
# 取当前页的文章信息
# 标题
regexs = '<h1.*?>(.*?)</h1>'
title = tools.get_info(html, regexs)
title = title and title[0] or ''
title = tools.del_html_tag(title)
# 内容
regexs = [
'<div id="main_content".*?>(.*?)</div>',
'<div class="yc_con_l">(.*?)<div class="txt_share_box"',
'<div id="slide_no_insert_default"></div>(.*?)</div>'
]
content = tools.get_info(html, regexs)
content = content and content[0] or ''
content = tools.del_html_tag(content)
log.debug('''
depth = %d
url = %s
title = %s
content = %s
''' % (depth + 1, source_url, title, content))
if content and title:
base_parser.add_article_info('article_text_info', website_id,
source_url, title, content)
# 更新source_url为done
base_parser.update_url('article_urls', source_url, Constance.DONE)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
source_url = url_info['url']
depth = url_info['depth']
website_id = url_info['site_id']
description = url_info['remark']
html = tools.get_html_by_urllib(source_url, code='GB2312')
if html == None:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 判断中英文
regex = '[\u4e00-\u9fa5]+'
chinese_word = tools.get_info(html, regex)
if not chinese_word:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 取当前页面的全部url
urls = tools.get_urls(html, STOP_URLS)
# 过滤掉外链接 添加到数据库
fit_url = tools.fit_url(urls, "people.com.cn")
for url in fit_url:
# log.debug('url = ' + url)
base_parser.add_url('article_urls', website_id, url, depth + 1)
# 取当前页的文章信息
# 标题
regexs = '<h1>(.*?)</h1>'
title = tools.get_info(html, regexs)
title = title and title[0] or ''
title = tools.replace_str(title, '&.*?;')
# 内容
regexs = [
'div class="box_pic"></div>(.*?)<div class="box_pic"></div>',
'<div class="content clear clearfix">(.*?)<div class="edit clearfix">',
'<div class="show_text">(.*?)<div class="edit">'
]
content = tools.get_info(html, regexs)
content = content and content[0] or ''
content = tools.del_html_tag(content)
log.debug('''
depth = %d
source_url = %s
title = %s
content = %s
''' % (depth, source_url, title, content))
if content and title:
base_parser.add_article_info('article_text_info', website_id,
source_url, title, content)
# 更新source_url为done
base_parser.update_url('article_urls', source_url, Constance.DONE)
def parser(url_info):
url_info['_id'] = str(url_info['_id'])
log.debug('处理 \n' + tools.dumps_json(url_info))
source_url = url_info['url']
depth = url_info['depth']
website_id = url_info['site_id']
description = url_info['remark']
html = tools.get_html_by_urllib(source_url)
if html == None:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 判断中英文
regex = '[\u4e00-\u9fa5]+'
chinese_word = tools.get_info(html, regex)
if not chinese_word:
base_parser.update_url('article_urls', source_url, Constance.EXCEPTION)
return
# 取当前页面的全部url
urls = tools.get_urls(html)
# 过滤掉外链接 添加到数据库
fit_url = tools.fit_url(urls, FIT_URLS)
for url in fit_url:
# log.debug('url = ' + url)
base_parser.add_url('article_urls', website_id, url, depth + 1)
# 取当前页的文章信息
# 标题
regexs = '<h1.*?>(.*?)</h1>'
title = tools.get_info(html, regexs)
title = title and title[0] or ''
title = tools.del_html_tag(title)
if title == '加载中...':
# 更新source_url为done
base_parser.update_url('article_urls', source_url, Constance.TODO)
return
# 内容
regexs = [
'id="artibody".*?>(.*?)<!-- 吸顶导航结束定位标记 -->',
'id="artibody".*?>(.*?)<div id="left_hzh_ad">',
'<!-- 正文内容 begin -->(.*?)<!-- 正文内容 end -->',
'id="article_content".*?>(.*?)<div class="spacer"></div>'
]
content = tools.get_info(html, regexs)
content = content and content[0] or ''
content = tools.del_html_tag(content)
log.debug('''
depth = %d
url = %s
title = %s
content = %s
''' % (depth + 1, source_url, title, content))
if content and title:
base_parser.add_article_info('article_text_info', website_id,
source_url, title, content)
# 更新source_url为done
base_parser.update_url('article_urls', source_url, Constance.DONE)