diff options
| author | kanzure <kanzure@gmail.com> | 2009-07-25 14:02:16 -0500 |
|---|---|---|
| committer | kanzure <kanzure@gmail.com> | 2009-07-25 14:02:16 -0500 |
| commit | 5d41cd8a4b07e2b44950456b4bec9b16822bd07b (patch) | |
| tree | ec0b4ac421a12dda4978e2b7034f5300a0f73f4a | |
| parent | 569ee998331cf612c95c0193e4182afb4d0790b4 (diff) | |
| download | pyscholar-5d41cd8a4b07e2b44950456b4bec9b16822bd07b.tar.gz pyscholar-5d41cd8a4b07e2b44950456b4bec9b16822bd07b.zip | |
working on doWeb
| -rw-r--r-- | packages/classes.py | 6 | ||||
| -rw-r--r-- | packages/tests.py | 9 | ||||
| -rw-r--r-- | tests/science-direct.html | 6 |
3 files changed, 13 insertions, 8 deletions
diff --git a/packages/classes.py b/packages/classes.py index 1f98afb..99807aa 100644 --- a/packages/classes.py +++ b/packages/classes.py @@ -34,10 +34,10 @@ class ScienceDirect(yaml.YAMLObject): return "journalArticle" return False def doWeb(self, doc, url): - if type(doc) == type(""): #then it's not BeautifulSoup + if type(doc) == type("huh"): #then it's not BeautifulSoup document = BSXPathEvaluator(doc) else: document = doc - if doc.evaluate('//*[contains(@src, "exportarticle_a.gif")]', doc, None, XPathResult.ANY_TYPE, None).iterateNext(): + if document.evaluate("//*[contains(@src, \"exportarticle_a.gif\")]", doc, None, XPathResult.ANY_TYPE, None).iterateNext(): articles = [] if (self.detectWeb(doc, url) == "multiple"): #search page @@ -66,5 +66,7 @@ class ScienceDirect(yaml.YAMLObject): if len(articles) == 0: print "ERROR: no items were found" return + print "articles = ", articles + print "result_sets = ", result_sets return diff --git a/packages/tests.py b/packages/tests.py index 42b2d8c..abf05ac 100644 --- a/packages/tests.py +++ b/packages/tests.py @@ -20,6 +20,15 @@ class TestScienceDirect(unittest.TestCase): doc = contents self.assertTrue(sci.detectWeb(doc, url)== "journalArticle") return + def test_doWeb(self): + sci = classes.ScienceDirect() + some_file = open("../tests/science-direct-search-results.html", "r") + contents = some_file.read() + some_file.close() + url = "http://www.sciencedirect.com/science?_ob=ArticleListURL&_method=list&_ArticleListID=966440345&_sort=r&view=c&_acct=C000059713&_version=1&_urlVersion=0&_userid=108429&md5=68c788df065c832e7749a7ae42d0261e" + doc = contents + print sci.doWeb(doc, url) + return if __name__ == '__main__': unittest.main() diff --git a/tests/science-direct.html b/tests/science-direct.html index 6892c4f..af1f02c 100644 --- a/tests/science-direct.html +++ b/tests/science-direct.html @@ -64,12 +64,6 @@ function getStyleObj(elem,parent) { <a href="http://www.sciencedirect.com.ezproxy.lib.utexas.edu/science?_ob=ArticleURL&_udi=B6TWB-4CGM8MB-1&_user=10&_rdoc=1&_fmt=&_orig=search&_sort=d&view=c&_acct=C000050221&_version=1&_urlVersion=0&_userid=10&md5=332a6427cb7f4df3e22a83f91c859c04#Skip%20Buttons" target="_top"><img src="science-direct_files/clear.gif" alt="Skip Main Navigation Links" title="Skip Main Navigation Links" border="0" width="10" height="1"></a> </td> <td align="center" bgcolor="#ffffff" valign="middle" nowrap="nowrap"> - - - - - - </td> <td style="padding-right: 0.2em;" align="right" width="37%" nowrap="nowrap"> <span style="font-size: 75%; font-family: arial,verdana,helvetica,sans-serif;"> |