effectCrawler 추가

git-svn-id: svn://192.168.0.12/source@311 8346c931-da38-4b9b-9d4c-e48b93cbd075

WebBasedCrawler/base/baseclasses.py

@@ -91,6 +91,7 @@ def find_elements_by_xpath(driver, tag, time=0):
     )
     return elements
 
+
 class Browser:
     def __init__(self, driver=None):
         self.driver = driver

WebBasedCrawler/effect/effectkakaostory.py

@@ -60,8 +60,6 @@ class BodyCrawler(object):
         self.soup = None
         self.section_activity = None
         self.set_soup_and_activity()
-        if not self.section_activity:
-            raise NotFoundElementError("section _activity is not Found")
 
     # calling point may differ
     def set_soup_and_activity(self):
@@ -231,11 +229,20 @@ class BodyCrawler(object):
         article_id = self.find_article_id()
         return 'channel' if article_id.startswith('ch/') else 'story'
 
+    def find_error(self):
+        error = self.soup.find('div', class_='info_error')
+        if error:
+            return True
+        else:
+            return False
+
     def get(self):
         """
         you need to put 'keyword_id'
         :return: dict for crawled body content
         """
+        if not self.section_activity:
+            raise NotFoundElementError("section _activity is not Found")
         content = dict()
         content['article_id'] = self.find_article_id()
         content['article_nickname'] = self.find_article_nickname()
@@ -421,6 +428,16 @@ class EffectKakaostory(object):
             wait(3)
             body_crawler = BodyCrawler(self.driver)
             reply_crawler = ReplyCrawler(self.driver)
+        except Exception as e:
+            raise effect.effecterror.OutDatedCrawler(str(e))
+
+        try:
+            error = body_crawler.find_error()
+        except Exception as e:
+            raise effect.effecterror.OutDatedCrawler(str(e))
+        if error:
+            raise effect.effecterror.DeletedUrlError("The URL is Deleted")
+        try:
             body = body_crawler.get()
             replies = reply_crawler.get()
         except Exception as e:

WebBasedCrawler/effect/resultsender.py

@@ -34,8 +34,8 @@ class ResultSender:
                 val_list.append(str(val))
             else:
                 val_list.append(self.conn.escape(self.re_emoji.sub(' ', str(val))))
-        return query + ",".join(key_list) + ") values (" + ",".join(val_list) + ")" # + " on duplicate key update " + \
- #              ','.join(map(lambda x:x[0] + '=' + x[1], zip(key_list, val_list)))
+        return query + ",".join(key_list) + ") values (" + ",".join(val_list) + ")" + " on duplicate key update " + \
+               ','.join(map(lambda x:x[0] + '=' + x[1], zip(key_list, val_list)))
 
     def send(self, table_name, dictionary):
         query = self._make_query(table_name, dictionary)

WebBasedCrawler/insta/instaparser.py

@@ -112,6 +112,7 @@ def parse_body_html(content):
             "article_form": "body",
             "article_profileurl": media["owner"]["profile_pic_url"],
             "article_order": str(media["comments"]["count"]),
+            "article_hit": str(media.get('video_views', 0)),
             "reply_url": str(media["likes"]["count"])
         }
         comments = postpage[0]["media"]["comments"]

WebBasedCrawler/kakao/kakaocrawl.py

@@ -336,7 +336,7 @@ class ReplyCrawler(object):
 
     def set_soup_and_activity(self):
         self.soup = BeautifulSoup(self.driver.page_source, parser_opt)
-        # There are many div.section _activity. But element we use is in div.cover_wrapper
+        # There are many div.section _activity. But a element we use is in div.cover_wrapper
         cover_wrapper = self.soup.find('div', class_='cover_wrapper')
         self.section_activity = cover_wrapper.find('div', class_='section _activity')
         self.ul = self.section_activity.find('ul', class_='list _listContainer')
@@ -345,7 +345,7 @@ class ReplyCrawler(object):
         previous_num_of_replies = 0
         while self.has_more():
             self.click_load_more_reply_btn()
-            # check number of replies before and after click_load_more_reply_btn()
+            # check the number of replies before and after click_load_more_reply_btn()
             # If These were equal, the link or ajax failed
             current_num_of_replies = self.get_num_of_replies()
             if previous_num_of_replies == current_num_of_replies: