Browse Source

Merge pull request #780 from kvch/google-play-movies-fix

XPATH engines: Google Play Music, Habrahabr, Yandex
Adam Tauber 8 years ago
parent
commit
75c58fd008
2 changed files with 7 additions and 6 deletions
  1. 2 2
      searx/engines/yandex.py
  2. 5 4
      searx/settings.yml

+ 2 - 2
searx/engines/yandex.py

@@ -29,10 +29,10 @@ language_map = {'ru': 'ru',
 base_url = 'https://yandex.{tld}/'
 base_url = 'https://yandex.{tld}/'
 search_url = 'search/?{query}&p={page}'
 search_url = 'search/?{query}&p={page}'
 
 
-results_xpath = '//div[@class="serp-item serp-item_plain_yes clearfix i-bem"]'
+results_xpath = '//li[@class="serp-item"]'
 url_xpath = './/h2/a/@href'
 url_xpath = './/h2/a/@href'
 title_xpath = './/h2/a//text()'
 title_xpath = './/h2/a//text()'
-content_xpath = './/div[@class="serp-item__text"]//text()'
+content_xpath = './/div[@class="text-container typo typo_text_m typo_line_m organic__text"]//text()'
 
 
 
 
 def request(query, params):
 def request(query, params):

+ 5 - 4
searx/settings.yml

@@ -192,6 +192,7 @@ engines:
   - name : gigablast
   - name : gigablast
     engine : gigablast
     engine : gigablast
     shortcut : gb
     shortcut : gb
+    timeout : 3.0
     disabled: True
     disabled: True
 
 
   - name : gitlab
   - name : gitlab
@@ -250,8 +251,8 @@ engines:
     engine        : xpath
     engine        : xpath
     search_url    : https://play.google.com/store/search?q={query}&c=movies
     search_url    : https://play.google.com/store/search?q={query}&c=movies
     url_xpath     : //a[@class="title"]/@href
     url_xpath     : //a[@class="title"]/@href
-    title_xpath   : //a[@class="title"]
-    content_xpath : //a[@class="subtitle"]
+    title_xpath   : //a[@class="title"]/@title
+    content_xpath : //a[contains(@class, "subtitle")]
     categories : videos
     categories : videos
     shortcut : gpm
     shortcut : gpm
     disabled : True
     disabled : True
@@ -282,8 +283,8 @@ engines:
     engine : xpath
     engine : xpath
     paging : True
     paging : True
     search_url : https://habrahabr.ru/search/page{pageno}/?q={query}
     search_url : https://habrahabr.ru/search/page{pageno}/?q={query}
-    url_xpath : //div[@class="search_results"]//a[@class="post_title"]/@href
-    title_xpath : //div[@class="search_results"]//a[@class="post_title"]
+    url_xpath : //div[@class="search_results"]//a[contains(@class, "post__title_link")]/@href
+    title_xpath : //div[@class="search_results"]//a[contains(@class, "post__title_link")]
     content_xpath : //div[@class="search_results"]//div[contains(@class, "content")]
     content_xpath : //div[@class="search_results"]//div[contains(@class, "content")]
     categories : it
     categories : it
     timeout : 4.0
     timeout : 4.0