本文整理汇总了Python中webkitpy.thirdparty.BeautifulSoup.BeautifulSoup类的典型用法代码示例。如果您正苦于以下问题：Python BeautifulSoup类的具体用法？Python BeautifulSoup怎么用？Python BeautifulSoup使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。
在下文中一共展示了BeautifulSoup类的15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: test_attachment_parsing
def test_attachment_parsing(self):
bugzilla = Bugzilla()
soup = BeautifulSoup(self._example_attachment)
attachment_element = soup.find("attachment")
attachment = bugzilla._parse_attachment_element(attachment_element, self._expected_example_attachment_parsing['bug_id'])
self.assertTrue(attachment)
self._assert_dictionaries_equal(attachment, self._expected_example_attachment_parsing)示例2: _parse_attachment_ids_request_query
def _parse_attachment_ids_request_query(self, page, since=None):
# Formats
digits = re.compile("\d+")
attachment_href = re.compile("attachment.cgi\?id=\d+&action=review")
# if no date is given, return all ids
if not since:
attachment_links = SoupStrainer("a", href=attachment_href)
return [int(digits.search(tag["href"]).group(0))
for tag in BeautifulSoup(page, parseOnlyThese=attachment_links)]
# Parse the main table only
date_format = re.compile("\d{4}-\d{2}-\d{2} \d{2}:\d{2}")
mtab = SoupStrainer("table", {"class": "requests"})
soup = BeautifulSoup(page, parseOnlyThese=mtab)
patch_ids = []
for row in soup.findAll("tr"):
patch_tag = row.find("a", {"href": attachment_href})
if not patch_tag:
continue
patch_id = int(digits.search(patch_tag["href"]).group(0))
date_tag = row.find("td", text=date_format)
if date_tag and datetime.strptime(date_format.search(date_tag).group(0), "%Y-%m-%d %H:%M") < since:
_log.info("Patch is old: %d (%s)" % (patch_id, date_tag))
continue
patch_ids.append(patch_id)
return patch_ids示例3: test_convert_vendor_prefix_js_paths
def test_convert_vendor_prefix_js_paths(self):
test_html = """<head>
<script src="/common/vendor-prefix.js">
</head>
"""
fake_dir_path = self.fake_dir_path('adapterjspaths')
converter = _W3CTestConverter(fake_dir_path, DUMMY_FILENAME)
oc = OutputCapture()
oc.capture_output()
try:
converter.feed(test_html)
converter.close()
converted = converter.output()
finally:
oc.restore_output()
new_html = BeautifulSoup(converted[1])
# Verify the original paths are gone, and the new paths are present.
orig_path_pattern = re.compile('\"/common/vendor-prefix.js')
self.assertEquals(len(new_html.findAll(src=orig_path_pattern)), 0, 'vendor-prefix.js path was not converted')
resources_dir = converter.path_from_webkit_root("LayoutTests", "resources")
new_relpath = os.path.relpath(resources_dir, fake_dir_path)
relpath_pattern = re.compile(new_relpath)
self.assertEquals(len(new_html.findAll(src=relpath_pattern)), 1, 'vendor-prefix.js relative path not correct')示例4: test_status_parsing
def test_status_parsing(self):
buildbot = BuildBot()
soup = BeautifulSoup(self._example_one_box_status)
status_table = soup.find("table")
input_rows = status_table.findAll("tr")
for x in range(len(input_rows)):
status_row = input_rows[x]
expected_parsing = self._expected_example_one_box_parsings[x]
builder = buildbot._parse_builder_status_from_row(status_row)
# Make sure we aren't parsing more or less than we expect
self.assertEquals(builder.keys(), expected_parsing.keys())
for key, expected_value in expected_parsing.items():
self.assertEquals(
builder[key],
expected_value,
(
"Builder %d parse failure for key: %s: Actual='%s' Expected='%s'"
% (x, key, builder[key], expected_value)
),
)示例5: _parse_result_count
def _parse_result_count(self, results_page):
result_count_text = BeautifulSoup(results_page).find(attrs={'class': 'bz_result_count'}).string
result_count_parts = result_count_text.strip().split(" ")
if result_count_parts[0] == "Zarro":
return 0
if result_count_parts[0] == "One":
return 1
return int(result_count_parts[0])示例6: test_failures_from_fail_row
def test_failures_from_fail_row(self):
row = BeautifulSoup("<tr><td><a>test.hml</a></td><td><a>expected image</a></td><td><a>25%</a></td></tr>")
test_name = unicode(row.find("a").string)
# Even if the caller has already found the test name, findAll inside _failures_from_fail_row will see it again.
failures = OutputCapture().assert_outputs(self, ORWTResultsHTMLParser._failures_from_fail_row, [row])
self.assertEqual(len(failures), 1)
self.assertEqual(type(sorted(failures)[0]), test_failures.FailureImageHashMismatch)
row = BeautifulSoup("<tr><td><a>test.hml</a><a>foo</a></td></tr>")
expected_stderr = "Unhandled link text in results.html parsing: foo. Please file a bug against webkitpy.\n"
OutputCapture().assert_outputs(self, ORWTResultsHTMLParser._failures_from_fail_row, [row], expected_stderr=expected_stderr)示例7: _revisions_for_builder
def _revisions_for_builder(self, builder):
soup = BeautifulSoup(self._fetch_builder_page(builder))
revisions = []
for status_row in soup.find('table').findAll('tr'):
revision_anchor = status_row.find('a')
table_cells = status_row.findAll('td')
if not table_cells or len(table_cells) < 3 or not table_cells[2].string:
continue
if revision_anchor and revision_anchor.string and re.match(r'^\d+$', revision_anchor.string):
revisions.append((int(revision_anchor.string), 'success' in table_cells[2].string))
return revisions示例8: verify_test_harness_paths
def verify_test_harness_paths(self, converter, converted, test_path, num_src_paths, num_href_paths):
if isinstance(converted, basestring):
converted = BeautifulSoup(converted)
resources_dir = converter.path_from_webkit_root("LayoutTests", "resources")
# Verify the original paths are gone, and the new paths are present.
orig_path_pattern = re.compile('\"/resources/testharness')
self.assertEquals(len(converted.findAll(src=orig_path_pattern)), 0, 'testharness src path was not converted')
self.assertEquals(len(converted.findAll(href=orig_path_pattern)), 0, 'testharness href path was not converted')
new_relpath = os.path.relpath(resources_dir, test_path)
relpath_pattern = re.compile(new_relpath)
self.assertEquals(len(converted.findAll(src=relpath_pattern)), num_src_paths, 'testharness src relative path not correct')
self.assertEquals(len(converted.findAll(href=relpath_pattern)), num_href_paths, 'testharness href relative path not correct')示例9: analyze_test
def analyze_test(self, test_contents=None, ref_contents=None):
"""Analyzes a file to determine if it's a test, what type of test, and what reference or support files it requires.
Returns: A dict which can have the properties:
"test": test file name.
"reference": related reference test file name if this is a reference test.
"reference_support_info": extra information about the related reference test and any support files.
"jstest": A boolean, whether this is a JS test.
If the given contents are empty, then None is returned.
"""
test_info = None
if test_contents is None and self.test_doc is None:
return test_info
if test_contents is not None:
self.test_doc = BeautifulSoup(test_contents)
if ref_contents is not None:
self.ref_doc = BeautifulSoup(ref_contents)
# First check if it's a reftest
matches = self.reference_links_of_type('match') + self.reference_links_of_type('mismatch')
if matches:
if len(matches) > 1:
# FIXME: Is this actually true? We should fix this.
_log.warning('Multiple references are not supported. Importing the first ref defined in %s',
self.filesystem.basename(self.filename))
try:
ref_file = self.filesystem.join(self.filesystem.dirname(self.filename), matches[0]['href'])
except KeyError:
# FIXME: Figure out what to do w/ invalid test files.
_log.error('%s has a reference link but is missing the "href"', self.filesystem)
return None
if self.ref_doc is None:
self.load_file(ref_file, True)
test_info = {'test': self.filename, 'reference': ref_file}
# If the ref file does not live in the same directory as the test file, check it for support files.
test_info['reference_support_info'] = {}
if self.filesystem.dirname(ref_file) != self.filesystem.dirname(self.filename):
reference_support_files = self.support_files(self.ref_doc)
if len(reference_support_files) > 0:
reference_relpath = self.filesystem.relpath(self.filesystem.dirname(
self.filename), self.filesystem.dirname(ref_file)) + self.filesystem.sep
test_info['reference_support_info'] = {'reference_relpath': reference_relpath, 'files': reference_support_files}
elif self.is_jstest():
test_info = {'test': self.filename, 'jstest': True}
elif self.options['all'] and '-ref' not in self.filename and 'reference' not in self.filename:
test_info = {'test': self.filename}
return test_info示例10: _parse_bug_dictionary_from_xml
def _parse_bug_dictionary_from_xml(self, page):
soup = BeautifulSoup(page)
bug = {}
bug["id"] = int(soup.find("bug_id").string)
bug["title"] = self._string_contents(soup.find("short_desc"))
bug["bug_status"] = self._string_contents(soup.find("bug_status"))
dup_id = soup.find("dup_id")
if dup_id:
bug["dup_id"] = self._string_contents(dup_id)
bug["reporter_email"] = self._string_contents(soup.find("reporter"))
bug["assigned_to_email"] = self._string_contents(soup.find("assigned_to"))
bug["cc_emails"] = [self._string_contents(element) for element in soup.findAll('cc')]
bug["attachments"] = [self._parse_attachment_element(element, bug["id"]) for element in soup.findAll('attachment')]
return bug示例11: user_dict_from_edit_user_page
def user_dict_from_edit_user_page(self, page):
soup = BeautifulSoup(page, convertEntities=BeautifulStoneSoup.HTML_ENTITIES)
user_table = soup.find("table", {"class": "main"})
user_dict = {}
for row in user_table("tr"):
label_element = row.find("label")
if not label_element:
continue # This must not be a row we know how to parse.
if row.find("table"):
continue # Skip the <tr> holding the groups table.
key = label_element["for"]
if "group" in key:
key = "groups"
value = user_dict.get("groups", set())
# We must be parsing a "tr" inside the inner group table.
(group_name, _) = self._group_name_and_string_from_row(row)
if row.find("input", {"type": "checkbox", "checked": "checked"}):
value.add(group_name)
else:
value = unicode(row.find("td").string).strip()
user_dict[key] = value
return user_dict示例12: _parse_bug_page
def _parse_bug_page(self, page):
soup = BeautifulSoup(page)
bug = {}
bug["id"] = int(soup.find("bug_id").string)
bug["title"] = unicode(soup.find("short_desc").string)
bug["reporter_email"] = str(soup.find("reporter").string)
bug["assigned_to_email"] = str(soup.find("assigned_to").string)
bug["cc_emails"] = [str(element.string)
for element in soup.findAll('cc')]
bug["attachments"] = [self._parse_attachment_element(element, bug["id"]) for element in soup.findAll('attachment')]
return bug示例13: _parse_twisted_directory_listing
def _parse_twisted_directory_listing(self, page):
soup = BeautifulSoup(page)
# HACK: Match only table rows with a class to ignore twisted header/footer rows.
file_rows = soup.find('table').findAll('tr', {'class': re.compile(r'\b(?:directory|file)\b')})
return [self._parse_twisted_file_row(file_row) for file_row in file_rows]示例14: _parse_mks_response_for_mks_id
def _parse_mks_response_for_mks_id(response):
# Part of the response may be encoded as HTML entities. We need to
# decode such entities so as to retrieve the text of <value>
decoded = BeautifulSoup(response, convertEntities=BeautifulSoup.XML_ENTITIES)
soup = BeautifulSoup(decoded.encode("UTF-8"))
return int(soup.find("value").string)示例15: _parse_quips
def _parse_quips(self, page):
soup = BeautifulSoup(page, convertEntities=BeautifulSoup.HTML_ENTITIES)
quips = soup.find(text=re.compile(r"Existing quips:")).findNext("ul").findAll("li")
return [unicode(quip_entry.string) for quip_entry in quips]