def parse_list_html(raw):
pattern = re.compile(r"(?s)<li>(.*?)<\/li>")
pattern_title = re.compile(r".*\d+年\d+月\d+日.*肺炎疫情.*")
p = ArticleParser()
for m in pattern.finditer(raw):
p.feed(m.groups()[0])
p.close()
latest_url = ""
for res in p.get_articles():
if pattern_title.match(res["title"]) is not None:
latest_url = root_url + res["href"][2:]
break
return latest_url
def parse_list_html(raw):
pattern = re.compile(r"(?s)<li class=\"list-group-item\">(.*?)<\/li>")
pattern_title = re.compile(r".*河南.*肺炎疫情.*情况")
p = ArticleParser()
for m in pattern.finditer(raw):
p.feed(m.groups()[0])
p.close()
latest_url = ""
for res in p.get_articles():
if pattern_title.match(res["title"]) is not None:
latest_url = base_url + res["href"]
break
return latest_url
def parse_list_html(raw):
pattern = re.compile(r"<li>(.*?)<\/li>")
pattern_title = re.compile(r"最新疫情通报...")
p = ArticleParser()
for m in pattern.finditer(raw):
p.feed(m.groups()[0])
p.close()
latest_url = ""
for res in p.get_articles():
if pattern_title.match(res["title"]) is not None:
latest_url = base_url + res["href"]
break
return latest_url
def parse_list_html(raw):
pattern = re.compile(r"(<td.*?<\/td>)")
pattern_title = re.compile(r".*肺炎疫情情况")
p = ArticleParser()
for m in pattern.finditer(raw):
p.feed(m.groups()[0])
p.close()
latest_url = ""
for res in p.get_articles():
if pattern_title.match(res["title"]) is not None:
latest_url = base_url + res["href"][2:]
break
return latest_url
def parse_list_html(raw):
pattern = re.compile(
r"(?s)<tr id=\"line17117_1\" height=\"20\">(.*?)<\/tr>")
pattern_title = re.compile(r".*肺炎疫情.*")
p = ArticleParser()
for m in pattern.finditer(raw):
p.feed(m.groups()[0])
p.close()
latest_url = ""
for res in p.get_articles():
if pattern_title.match(res["title"]) is not None:
latest_url = base_url + res["href"][5:]
break
return latest_url