本文整理汇总了Python中DB.db方法的典型用法代码示例。如果您正苦于以下问题:Python DB.db方法的具体用法?Python DB.db怎么用?Python DB.db使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类DB
的用法示例。
在下文中一共展示了DB.db方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: run
# 需要导入模块: import DB [as 别名]
# 或者: from DB import db [as 别名]
def run(self):
"""
Do the actual downloading of documents
"""
# Grab the URLs to download
db = DB.db()
i = 0
# Loop through them and actually download and save
while 1:
urls = db.multirow("select url from rdfs_grab_urls(%d, %s, '90 days'::reltime)" % (self.n_docs, db.dbstr(self.getName())))
self.log("urls to dl (run %s): %s" % (i,len(urls)))
i += 1
if len(urls) == 0:
break
for url_row in urls:
url= url_row["url"]
self.log("grabbing %s" % url)
try:
doc = document.Document(url)
doc.grab()
except:
self.log("couldn't download URL %s" % url)
self.touchURL(db, url, 'comatose')
continue
self.log("done grabbing %s" % url)
# If we get here, then the URL has been successfully downloaded and,
# even if we fail later, we don't want to have to deal with reloading it again
self.touchURL(db, url)
try:
doc.parse()
except RuntimeError, (strerror):
self.log("couldn't parse URL %s: %s" % (url,strerror))
continue
except:
self.log("couldn't parse URL %s" % url)
示例2: slash
# 需要导入模块: import DB [as 别名]
# 或者: from DB import db [as 别名]
url = self.url
db_url = db.dbstr(url)
# Fix the license_url if it has no end slash (old licenses!)
# TODO: change this to query the license from CC and use the built-in 302 redirect to do the right thing
license_url = work.licenses()[0]
if license_url[-1] != "/":
license_url += "/"
db_license_url = db.dbstr(license_url)
# First make sure the URL is in there (in case it's changed)
db.perform("select rdfs_url_new(%s, %d)" % (db_url, Document.method_id))
query = "select rdfs_store_document(%s, rdfs_get_license_id(%s), %s, %s, %s, %s, %s, %s)" % (db_url, db_license_url, db_title, db_date, db_description, db_creator, db_type, db_raw_text)
# do the update in the DB
db.perform(query.encode('utf-8','ignore'))
# Test
if __name__ == "__main__":
#doc= Document('http://shyflower.com/art/Themes/AllAmerican/amer.htm')
#doc= Document('http://commoncontent.org/catalog/images/clipart/505/xml')
#doc = Document('http://thecrankyone.diaryland.com/lotsanothin.html')
#doc = Document('http://thejugglers.org/archives/2003_05.php')
#doc = Document('http://gondwanaland.com/ml/')
doc = Document(sys.argv[1])
doc.grab()
doc.parse()
doc.store(DB.db())