diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/devryzom.py | 65 |
1 files changed, 18 insertions, 47 deletions
diff --git a/src/devryzom.py b/src/devryzom.py index 80afab5..8d31524 100644 --- a/src/devryzom.py +++ b/src/devryzom.py @@ -24,8 +24,6 @@ number_of_results = 5 # Doku is OpenSearch compatible base_url = 'https://dev.ryzom.com' search_url = '/search?wiki_pages=1&{query}' -#search_url = '/wikhan/?do=search'\ -# '&{query}' # TODO '&startRecord={offset}'\ # TODO '&maximumRecords={limit}'\ @@ -45,62 +43,35 @@ def response(resp): doc = fromstring(resp.text) - # parse results - # Quickhits + # Search i = 0 for r in doc.xpath('//dl[@id="search-results"]/dt'): try: res_url = r.xpath('.//a/@href')[-1] - except: - continue - - if not res_url: - continue - - title = extract_text(r.xpath('.//a')) + title = extract_text(r.xpath('.//a')) - i = i + 1 + i = i + 1 - y = 0 + y = 0 + for s in doc.xpath('//dl[@id="search-results"]/dd'): + y = y + 1 + if y == i: + content = extract_text(s.xpath('.//span[@class="description"]')) + dataBrut = extract_text(s.xpath('.//span[@class="author"]')) - for s in doc.xpath('//dl[@id="search-results"]/dd'): - y = y + 1 - if y == i: - content = extract_text(s.xpath('.//span[@class="description"]')) - - dataBrut = extract_text(s.xpath('.//span[@class="author"]')) - data = dataBrut.split(' ') - date = data[0].split('/') + data = dataBrut.split(' ') + date = data[0].split('/') + # append result + results.append({'title': title, + 'content': content, + 'url': base_url + res_url, + 'publishedDate': datetime(int(date[2]), int(date[0]), int(date[1]), 0, 0, 0)}) - # append result - results.append({'title': title, - 'content': content, - 'url': base_url + res_url, - 'publishedDate': datetime(int(date[2]), int(date[0]), int(date[1]), 0, 0, 0)}) - # append result - #results.append({'content': content}) - - # Search results - #for r in doc.xpath('//dl[@class="search_results"]/*'): - # try: - # if r.tag == "dt": - # res_url = r.xpath('.//a[@class="wikilink1"]/@href')[-1] - # title = extract_text(r.xpath('.//a[@class="wikilink1"]/@title')) - # elif r.tag == "dd": - # content = extract_text(r.xpath('.')) - - # append result - # results.append({'title': title, - # 'content': content, - # 'url': base_url + res_url}) - # except: - # continue - - # if not res_url: - # continue + except: + continue # return results return results |