diff options
| author | Markus Heiser <markus.heiser@darmarIT.de> | 2021-11-27 12:59:39 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2021-11-27 12:59:39 +0100 |
| commit | 11ba7f294ff1db37822dd5e7ec75cab5b30deccd (patch) | |
| tree | b690dce6ca45de6dc353ff010b36436453efb58b | |
| parent | f0db33e14b5b443eedc25f5aeba6cd330476c851 (diff) | |
| parent | 6e06618e0c44b52d5d322a7f5d35f1a8a7a7d247 (diff) | |
Merge pull request #554 from return42/fix-google-video
[fix] google-videos engine: ignore news articles
| -rw-r--r-- | searx/engines/google_videos.py | 12 |
1 files changed, 5 insertions, 7 deletions
diff --git a/searx/engines/google_videos.py b/searx/engines/google_videos.py index abf046f4c..77b0ab260 100644 --- a/searx/engines/google_videos.py +++ b/searx/engines/google_videos.py @@ -154,25 +154,23 @@ def response(resp): # parse results for result in eval_xpath_list(dom, '//div[contains(@class, "g ")]'): - # google *sections* + # ignore google *sections* if extract_text(eval_xpath(result, g_section_with_header)): logger.debug("ingoring <g-section-with-header>") continue - title = extract_text(eval_xpath_getindex(result, title_xpath, 0)) - url = eval_xpath_getindex(result, './/div[@class="dXiKIc"]//a/@href', 0) - - # <img id="vidthumb1" ...> + # ingnore articles without an image id / e.g. news articles img_id = eval_xpath_getindex(result, './/g-img/img/@id', 0, default=None) if img_id is None: - logger.error("no img_id for: %s" % result) + logger.error("no img_id found in item %s (news article?)", len(results) + 1) continue img_src = vidthumb_imgdata.get(img_id, None) if not img_src: - logger.error("no vidthumb imgdata for: %s" % img_id) img_src = thumbs_src.get(img_id, "") + title = extract_text(eval_xpath_getindex(result, title_xpath, 0)) + url = eval_xpath_getindex(result, './/div[@class="dXiKIc"]//a/@href', 0) length = extract_text(eval_xpath( result, './/div[contains(@class, "P7xzyf")]/span/span')) c_node = eval_xpath_getindex(result, './/div[@class="Uroaid"]', 0) |