def scratch(self, url):
try:
req = urllib.request.Request(url)
result = urllib.request.urlopen(req).read()
html = result.decode("utf-8", 'ignore')
return html
except Exception as e:
logutil.log("CnbetaSpider", e)
return None
def fetchItemList(self):
htmlSoup = BeautifulSoup(self.mainHtml, "html.parser")
listDiv = htmlSoup.find(attrs={"class": "alllist"}).find(attrs={"class": "items_area"})
itemRawList = listDiv.find_all(attrs={"class": "item"})
for item in itemRawList:
try:
article = CnbetaArticle()
titleTag = item.find(attrs={"class": "title"}).find("a")
contentTag = item.find("span", attrs={"class": "newsinfo"}).find("p")
article.title = "".join(titleTag.contents)
article.url = self.targetMainUrl + titleTag["href"]
article.cover = item.find("div", attrs={"class": "pic"}).find("a").find("img")['src']
briefStr = contentTag.renderContents().decode("utf-8")
article.brief = briefStr
self.itemList.append(article)
except Exception as e:
# print(e)
pass
logutil.log("CnbetaSpider", "getItemList finished")
