(url)
| 35 | return zip(new_items, new_urls) |
| 36 | |
| 37 | def Spider(url): |
| 38 | i = 0 |
| 39 | print "downloading ", url |
| 40 | myPage = requests.get(url).content.decode("gbk") |
| 41 | # myPage = urllib2.urlopen(url).read().decode("gbk") |
| 42 | myPageResults = Page_Info(myPage) |
| 43 | save_path = u"网易新闻抓取" |
| 44 | filename = str(i)+"_"+u"新闻排行榜" |
| 45 | StringListSave(save_path, filename, myPageResults) |
| 46 | i += 1 |
| 47 | for item, url in myPageResults: |
| 48 | print "downloading ", url |
| 49 | new_page = requests.get(url).content.decode("gbk") |
| 50 | # new_page = urllib2.urlopen(url).read().decode("gbk") |
| 51 | newPageResults = New_Page_Info(new_page) |
| 52 | filename = str(i)+"_"+item |
| 53 | StringListSave(save_path, filename, newPageResults) |
| 54 | i += 1 |
| 55 | |
| 56 | |
| 57 | if __name__ == '__main__': |
no test coverage detected