diff options
| author | Cengiz Kaygusuz <cngkaygusuz@gmail.com> | 2017-11-20 20:46:39 -0500 |
|---|---|---|
| committer | Cengiz Kaygusuz <cngkaygusuz@gmail.com> | 2017-11-20 20:46:39 -0500 |
| commit | 27e183a78c8062ed7c2bbb91655a5e56cd697bba (patch) | |
| tree | 88fd355a0cc6da4c130582e092d702836596cbb2 /examples/urlExtractor.py | |
| parent | 4ba589cf13588e90992e23deb5a9784340efd2cc (diff) | |
| download | pyparsing-git-27e183a78c8062ed7c2bbb91655a5e56cd697bba.tar.gz | |
Move src to root
Diffstat (limited to 'examples/urlExtractor.py')
| -rw-r--r-- | examples/urlExtractor.py | 33 |
1 files changed, 33 insertions, 0 deletions
diff --git a/examples/urlExtractor.py b/examples/urlExtractor.py new file mode 100644 index 0000000..2c66d78 --- /dev/null +++ b/examples/urlExtractor.py @@ -0,0 +1,33 @@ +# URL extractor
+# Copyright 2004, Paul McGuire
+from pyparsing import makeHTMLTags, SkipTo, pyparsing_common
+import urllib.request
+from contextlib import closing
+import pprint
+
+linkOpenTag, linkCloseTag = makeHTMLTags('a')
+
+linkBody = SkipTo(linkCloseTag)
+linkBody.setParseAction(pyparsing_common.stripHTMLTags)
+linkBody.addParseAction(lambda toks: ' '.join(toks[0].strip().split()))
+
+link = linkOpenTag + linkBody("body") + linkCloseTag.suppress()
+
+# Go get some HTML with some links in it.
+with closing(urllib.request.urlopen("http://www.yahoo.com")) as serverListPage:
+ htmlText = serverListPage.read().decode("UTF-8")
+
+# scanString is a generator that loops through the input htmlText, and for each
+# match yields the tokens and start and end locations (for this application, we are
+# not interested in the start and end values).
+for toks,strt,end in link.scanString(htmlText):
+ print(toks.asList())
+
+# Create dictionary from list comprehension, assembled from each pair of tokens returned
+# from a matched URL.
+pprint.pprint(
+ dict((toks.body, toks.href) for toks,strt,end in link.scanString(htmlText))
+ )
+
+
+
|