Dekker1/Fourmi
Archived
1
0
Fork 0
Code

final documentation

Browse Source
This commit is contained in:
Bas Vb 2014-06-10 22:46:50 +02:00
parent de474fea31
commit a1859f2ec2
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
FourmiCrawler/sources/WikipediaParser.py
View File

@ -79,6 +79,13 @@ class WikipediaParser(Source):
return item_list
def parse_chembox(self, sel, items):
"""
Scrape data from chembox infobox on wikipedia.
:param sel: The selector with the html-information of the page to parse
:param items: the list of items where the result have to be stored in
:return: items: the list of items with the new found and stored items
"""
tr_list = sel.xpath('.//table[@class="infobox bordered"]//td[not(@colspan)]'). \
xpath('normalize-space(string())')
prop_names = tr_list[::2]
@ -93,6 +100,13 @@ class WikipediaParser(Source):
return items
def parse_drugbox(self, sel, items):
"""
Scrape data from drugbox infobox on wikipedia.
:param sel: The selector with the html-information of the page to parse
:param items: the list of items where the result have to be stored in
:return: items: the list of items with the new found and stored items
"""
tr_list2 = sel.xpath('.//table[@class="infobox"]//tr')
log.msg('dit: %s' % tr_list2, level=log.DEBUG)
for tablerow in tr_list2: