def parse_question(self, response):
# 处理question页面，从页面中提取具体的quesiton item
if "QuestionHeader-title" in response.text:
# 处理新版本的页面
match_obj = re.match("(.*zhihu.com/question/(\d+))(/|$).*",
response.url)
if match_obj:
question_id = int(match_obj.group(2))
item_loader = ItemLoader(item=ZhihuQuestionItem(),
response=response)
item_loader.add_css("title", "h1.QuestionHeader-title::text")
item_loader.add_css("content", ".QuestionHeader-detail")
item_loader.add_value("url", response.url)
item_loader.ad_value("zhihu_id", question_id)
item_loader.add_css("answer_num", ".List-headerText span::text")
item_loader.add_css("comments_num",
"Questionheader-actions button::text")
item_loader.add_css("watch_user_num", ".NumberBoard-value::text")
item_loader.add_css("topics",
".QuestionHeader-topics .Popover::text")
question_item = item_loader.load_item()
else:
# 处理知乎旧版本
match_obj = re.match("(.*zhihu.com/question/(\d+))(/|$).*",
response.url)
if match_obj:
question_id = int(match_obj.group(2))
item_loader = ItemLoader(item=ZhihuQuestionItem(),
response=response)
item_loader.add_css("title", ".zh-question-title h2 a::text")
item_loader.add_css("content", "#zh-question-detail")
item_loader.add_value("url", response.url)
item_loader.add_value("zhihu_id", question_id)
item_loader.add_css("answer_num", ".List-headerText span::text")
item_loader.add_css(
"comments_num",
"#zh-question-meta-wrap a[name='addcomment']::text")
item_loader.add_css("watch_user_num",
"#zh-question-side-header-wrap::text")
item_loader.add_css("topics", ".zm-tag-editor-labels a::text")
question_item = item_loader.load_item()
pass
