def process(thread):
for url in pages(thread):
stanza_template=Template(u"""
{*
<table id="firstAuthor">
<tr>
<td>
<a>${author}</a> 发表日期：{{ [stanzas].datetime }}
</td>
</tr>
</table>
<div id="pContentDiv">
<div class="post">
{{ [stanzas].content|html }}
</div>
</div>
*}
{*
<table>
<tr>
<td>
<a>${author}</a> 回复日期：{{ [stanzas].datetime }}
</td>
</tr>
</table>
<div class="post">
{{ [stanzas].content|html }}
</div>
*}
""")
logging.info(thread['author'])
pattern=scrapemark.compile(stanza_template.substitute(author=thread['author']))
logging.info(pattern)
thread['stanzas'][url]=scrapemark.scrape(pattern, url=url, encoding=encoding)['stanzas']
logging.info(thread['stanzas'][url])
def process():
url='http://www.tianya.cn/publicforum/content/develop/1/905898.shtml'
template=Template(u"""
{*
<table id="firstAuthor">
<tr>
<td>
<a>${author}</a> 发表日期：{{ [stanzas].datetime }}
</td>
</tr>
</table>
<div id="pContentDiv">
<div class="post">
{{ [stanzas].content }}
</div>
</div>
*}
{*
<table>
<tr>
<td>
<a>${author}</a> 回复日期：{{ [stanzas].datetime }}
</td>
</tr>
</table>
<div class="post">
{{ [stanzas].content }}
</div>
*}
""")
pattern=template.substitute(author=u'flp713')
pattern=scrapemark.compile(pattern)
stanzas=scrapemark.scrape(pattern, url=url, encoding=encoding)['stanzas']
return stanzas