本文整理汇总了Python中variety.Util.Util.html_soup方法的典型用法代码示例。如果您正苦于以下问题：Python Util.html_soup方法的具体用法？Python Util.html_soup怎么用？Python Util.html_soup使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类variety.Util.Util的用法示例。
在下文中一共展示了Util.html_soup方法的5个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: get_for_author
# 需要导入模块: from variety.Util import Util [as 别名]
# 或者: from variety.Util.Util import html_soup [as 别名]
def get_for_author(self, author):
logger.info(lambda: "Fetching quotes from Goodreads for author=%s" % author)
url = iri2uri(u"https://www.goodreads.com/quotes/search?utf8=\u2713&q=%s" % author)
soup = Util.html_soup(url)
page_links = list(Util.safe_map(int,
[pagelink.contents[0] for pagelink in
soup.find_all(href=re.compile('quotes/search.*page='))]))
if page_links:
page = random.randint(1, max(page_links))
url = iri2uri(u"https://www.goodreads.com/quotes/search?utf8=\u2713&q=%s&page=%d" % (author, page))
soup = Util.html_soup(url)
return self.get_from_soup(url, soup)示例2: get_for_keyword
# 需要导入模块: from variety.Util import Util [as 别名]
# 或者: from variety.Util.Util import html_soup [as 别名]
def get_for_keyword(self, keyword):
logger.info(lambda: "Fetching quotes from Goodreads for keyword=%s" % keyword)
url = iri2uri(u"https://www.goodreads.com/quotes/tag?utf8=\u2713&id=%s" % keyword)
soup = Util.html_soup(url)
page_links = list(Util.safe_map(int,
[pagelink.contents[0] for pagelink in
soup.find_all(href=re.compile('quotes/tag.*page='))]))
if page_links:
page = random.randint(1, max(page_links))
url = iri2uri(u"https://www.goodreads.com/quotes/tag?utf8=\u2713&id=%s&page=%d" % (keyword, page))
soup = Util.html_soup(url)
return self.get_from_soup(url, soup)示例3: download_one
# 需要导入模块: from variety.Util import Util [as 别名]
# 或者: from variety.Util.Util import html_soup [as 别名]
def download_one(self):
min_download_interval, min_fill_queue_interval = self.parse_server_options("wallhaven", 0, 0)
if time.time() - WallhavenDownloader.last_download_time < min_download_interval:
logger.info(
lambda: "Minimal interval between Wallhaven downloads is %d, skip this attempt" % min_download_interval
)
return None
logger.info(lambda: "Downloading an image from Wallhaven.cc, " + self.location)
logger.info(lambda: "Queue size: %d" % len(self.queue))
if not self.queue:
if time.time() - self.last_fill_time < min_fill_queue_interval:
logger.info(
lambda: "Wallhaven queue empty, but minimal interval between fill attempts is %d, "
"will try again later" % min_fill_queue_interval
)
return None
self.fill_queue()
if not self.queue:
logger.info(lambda: "Wallhaven queue still empty after fill request")
return None
WallhavenDownloader.last_download_time = time.time()
wallpaper_url = self.queue.pop()
logger.info(lambda: "Wallpaper URL: " + wallpaper_url)
s = Util.html_soup(wallpaper_url)
src_url = s.find("img", id="wallpaper")["src"]
logger.info(lambda: "Image src URL: " + src_url)
extra_metadata = {}
try:
extra_metadata["keywords"] = [el.text.strip() for el in s.find_all("a", {"class": "tagname"})]
except:
pass
try:
purity = s.find("div", "sidebar-content").find("label", "purity").text.lower()
sfw_rating = {"sfw": 100, "sketchy": 50, "nsfw": 0}[purity]
extra_metadata["sfwRating"] = sfw_rating
if self.parent and self.parent.options.safe_mode and sfw_rating < 100:
logger.info(
lambda: "Skipping non-safe download from Wallhaven. "
"Is the source %s suitable for Safe mode?" % self.location
)
return None
except:
pass
return self.save_locally(wallpaper_url, src_url, extra_metadata=extra_metadata)示例4: search
# 需要导入模块: from variety.Util import Util [as 别名]
# 或者: from variety.Util.Util import html_soup [as 别名]
def search(self, page=None):
url = self.url
if page:
url = url + ("&" if "?" in self.url else "?") + "page=" + str(page)
logger.info(lambda: "Performing wallhaven search: url=%s" % url)
soup = Util.html_soup(url)
result_count = None
try:
result_count = int(soup.find("header", {"class": "listing-header"}).find("h1").text.split()[0])
except:
pass
return soup, result_count示例5: fetch
# 需要导入模块: from variety.Util import Util [as 别名]
# 或者: from variety.Util.Util import html_soup [as 别名]
def fetch(url, xml=False):
return Util.xml_soup(url) if xml else Util.html_soup(url)