Python DOM.by_attrの例

コード例 #1

ファイル: 12-dom.py プロジェクト: clips/pattern

dom = DOM(url.download(cached=True))

for e in dom.by_tag("header.post-block__header")[:5]:
    for a in e.by_tag("h2.post-block__title")[:1]:
        print(plaintext(a.content))
        for h in a.by_tag("a.post-block__title__link")[:1]:
            print(h.attrs["href"])
        print("")
print("\n")

header = dom.by_class("river__title")[0]
print(header.content)
print("\n")


title_image = dom.by_attr(name="msapplication-TileImage")[0]
print(title_image.attrs['content'])
print("\n")


url = URL("https://techcrunch.com")
dom = DOM(url.download(cached=True))
for k in dom.by_class("post-block__title__link"):
    print(k.content.strip())
    print("")

print("\n")

for e in dom("header:post-block__header h2:post-block__title a:post-block__title__link"):
    print(e.content.strip())
    print(e.attrs["href"])

コード例 #2

ファイル: 12-dom.py プロジェクト: Abhishek-1/temp

url = URL("https://techcrunch.com/startups/")
dom = DOM(url.download(cached=True))

for e in dom.by_tag("header.post-block__header")[:5]:
    for a in e.by_tag("h2.post-block__title")[:1]:
        print(plaintext(a.content))
        for h in a.by_tag("a.post-block__title__link")[:1]:
            print(h.attrs["href"])
        print("")
print("\n")

header = dom.by_class("river__title")[0]
print(header.content)
print("\n")

title_image = dom.by_attr(name="msapplication-TileImage")[0]
print(title_image.attrs['content'])
print("\n")

url = URL("https://techcrunch.com")
dom = DOM(url.download(cached=True))
for k in dom.by_class("post-block__title__link"):
    print(k.content.strip())
    print("")

print("\n")

for e in dom(
        "header:post-block__header h2:post-block__title a:post-block__title__link"
):
    print(e.content.strip())