def parse(self, text):
soup = BeautifulSoup(text, "lxml")
table = soup.find('table')
trs = table.find_all('tr')
data = []
for tr in trs[1:]:
index = tr.find(class_="first")
if not index:
continue
index = int(index.text)
keyword = tr.find(class_="keyword").find('a').text
href = tr.find(class_="keyword").find('a')['href']
keyword = keyword.replace('\n', '').replace('\t', '').strip()
search_index = tr.find(class_="last").text
search_index = int(search_index)
data.append({
'num': index,
'title': keyword,
'score': search_index,
'url': href
})
res_dict = {}
res_dict["list"] = data
res_dict["date"] = nowStr()
res_dict["logo"] = logo_url
res_dict["color"] = bgcolor
return res_dict
def parse(self, text):
html_xpath = etree.HTML(text)
data = html_xpath.xpath('//*[@id="pl_top_realtimehot"]/table/tbody/tr')
# print(data)
res_list = []
num = 0
for tr in (data):
cur_dict = {}
title = tr.xpath('./td[2]/a/text()')
hot_score = tr.xpath('./td[2]/span/text()')
url = host + tr.xpath('./td[2]/a')[0].get("href")
tag = tr.xpath('./td[3]/i/text()')
# print(url)
# if len(tag) != 0: print(tag[0])
# 过滤第 0 条
if num == 0:
pass
else:
cur_dict["title"] = title[0]
cur_dict["score"] = hot_score[0]
cur_dict["num"] = num
cur_dict["url"] = url
if len(tag): cur_dict["tag"] = tag[0]
res_list.append(cur_dict)
num += 1
res_dict = {}
res_dict["list"] = res_list
res_dict["date"] = nowStr()
res_dict["logo"] = logo_url
res_dict["color"] = bgcolor
return res_dict
def parse(self, text):
html_xpath = etree.HTML(text)
data = html_xpath.xpath('//*[@class="rank-item"]')
# print(data)
res_list = []
num = 0
for idx, item in enumerate(data):
cur_dict = {}
title = item.xpath(
'./div[@class="content"]/div[@class="info"]/a/text()')
hot_score = item.xpath(
'./div[@class="content"]/div[@class="info"]/div[@class="pts"]/div/text()'
)
url = item.xpath(
'./div[@class="content"]/div[@class="info"]/a')[0].get("href")
cur_dict["title"] = title[0]
cur_dict["score"] = hot_score[0]
cur_dict["num"] = idx + 1
cur_dict["url"] = url
res_list.append(cur_dict)
res_dict = {}
res_dict["list"] = res_list
res_dict["date"] = nowStr()
res_dict["logo"] = logo_url
res_dict["color"] = bgcolor
return res_dict
def parse(self, text):
html_xpath = etree.HTML(text)
data = html_xpath.xpath(
'//*[@id="j-bbs-hotpost"]/*[@class="m-box"]/ul/li')
# print(data)
res_list = []
num = 0
for idx, li in enumerate(data):
cur_dict = {}
title = li.xpath('.//p[@class="title"]/text()')
# hot_score = tr.xpath('./td[2]/span/text()')
url = li.xpath('./a')[0].get("href")
# 过滤第 0 条
cur_dict["title"] = title[0]
cur_dict["score"] = ""
cur_dict["num"] = idx + 1
cur_dict["url"] = url
res_list.append(cur_dict)
res_dict = {}
res_dict["list"] = res_list
res_dict["date"] = nowStr()
res_dict["logo"] = logo_url
res_dict["color"] = bgcolor
return res_dict
def parse(self, data):
thelist = findKey(data, "hotList")
res_list = []
for idx, entry in enumerate(thelist):
cur_dict = {}
cur_dict["title"] = findKey(entry, "titleArea")["text"]
cur_dict["url"] = findKey(entry, "link")["url"]
cur_dict["num"] = idx + 1
cur_dict["score"] = findKey(entry, "metricsArea")["text"]
if findKey(entry, "excerptArea")["text"]:
cur_dict["extra"] = findKey(entry, "excerptArea")["text"]
res_list.append(cur_dict)
res_dict = {}
res_dict["list"] = res_list
res_dict["date"] = nowStr()
res_dict["logo"] = logo_url
res_dict["color"] = bgcolor
return res_dict
def parse(self, data):
# print(text)
topic_list = findKey(findKey(data, "bang_topic"), "topic_list")
# print(topic_list)
res_list = []
num = 0
for idx,item in enumerate(topic_list):
cur_dict = {}
cur_dict["title"] = item["topic_name"]
cur_dict["score"] = item["discuss_num"]
cur_dict["num"] = idx + 1
cur_dict["url"] = item["topic_name"]
cur_dict["text"] = item["topic_desc"]
cur_dict["img"] = item["topic_pic"]
res_list.append(cur_dict)
res_dict = {}
res_dict["list"] = res_list
res_dict["date"] = nowStr()
res_dict["logo"] = logo_url
res_dict["color"] = bgcolor
return res_dict