bookmark_tasks.py 文件源码

def fulltext_extract(bookmark):
    browser = webdriver.PhantomJS(service_args=[
        "--ignore-ssl-errors=true",
        "--ssl-protocol=tlsv1",
        "--load-images=no"])
    fulltext_bookmark = Bookmark.query.get(bookmark.id)
    browser.get(fulltext_bookmark.main_url)
    body = browser.find_element_by_tag_name('body')
    bodytext = body.text
    soup = BeautifulSoup4(bodytext)
    full_text = soup.text
    full_text = " ".join(full_text.split())
    full_text = full_text.replace('\n', '')
    full_text = full_text.encode('utf-8')
    fulltext_bookmark.full_text = full_text
    db.session.commit()
    browser.quit()