Beispiel #1
0
 def extract_first_journal_url(self, journal_url, response):
     first_entry_url_xpath = "/html/body/table//tr[4]/td/table/tr//td[2]/table//tr[1]"
     first_entry_url = Selector(response=response).xpath(first_entry_url_xpath + "//a[contains(text(), 'First')]")
     if first_entry_url:
         # Not on the first journal page. Record the first entry url.
         first_entry_url = first_entry_url.__getattribute__("href")
         pass
     # Already on the first journal page.
     return first_entry_url