def testRows(self, MockClass):
self.setUpMock(MockClass)
html = self.addingMachine.main()
p = MyHtmlParser()
p.feed(html)
self.assertEqual(p.allParagraphText.strip(),
"The sum of 2 and 3 is 5", "got {0}".format(p.allParagraphText))
def testRows(self, MockClass):
self.setUpMock(MockClass)
html = self.addingMachine.main()
p = MyHtmlParser()
p.feed(html)
self.assertEqual(p.allParagraphText.strip(), "The sum of 2 and 3 is 5",
"got {0}".format(p.allParagraphText))
def testHtml(self):
text = self.addingMachine.run("AddingMachine.csv")
parse = MyHtmlParser()
parse.feed(text)
lines = parse.allParagraphText.splitlines()
lineCount = lines.count("The sum of 1 and 2 is 3")
self.assertEqual(lineCount, 1, "Bad sums".format("Line count: {0}".format(lineCount)))
def testHtml(self):
text = self.addingMachine.run("AddingMachine.csv")
parse = MyHtmlParser()
parse.feed(text)
lines = parse.allParagraphText.splitlines()
lineCount = lines.count("The sum of 1 and 2 is 3")
self.assertEqual(
lineCount, 1,
"Bad sums".format("Line count: {0}".format(lineCount)))
def main():
url = "https://www.airbnb.com/careers/departments/business-development"
html = HtmlRetriever(url)
print "length of html string:", len(html)
parser = MyHtmlParser()
parser.feed(html)
print "parser links 2: ", parser.links
def parserMetaInfo(context):
# 解析首页出来的新内容，得到title，url，
my = MyHtmlParser()
my.feed(context)
for k in my.kvs:
print k + " , " + my.kvs[k]
now = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
value = [k, my.kvs[k]]
#sql = "insert into blog_news(title,url,source) values('%s', '%s', 'jobbole.com')"
sql = "insert into blog_news(title,url,source,create_time,update_time) \
values('" + k + "', '" + my.kvs[k] + "','jobbole.com','" + now + "', '" + now + "')"
print sql
commitDate(sql)
def _fetch_and_parse(self, job_id, url, depth):
"""
Fetch a webpage and parse it for links and images.
Arguments:
job_id: intefer job id.
url: string URL.
depth: integer current depth.
Returns: None.
"""
html_parser = MyHtmlParser(url)
request_headers = {'User-Agent': self.user_agent}
request = urllib_Request(url, headers=request_headers)
try:
webpage = urlopen(request).read().decode()
except Exception as error:
data.redis.set(url, 'failed')
return
try:
html_parser.feed(webpage)
except (HTMLParseError) as error:
data.redis.set(url, 'failed')
return
data.add_webpages(url, html_parser.hyperlinks, depth)
data.redis.set(url, 'complete')
data.complete_crawl(url)
if 0 < depth and self._active and not data.job_is_aborted(job_id):
if html_parser.hyperlinks:
data.redis.sadd('job' + str(job_id), *html_parser.hyperlinks)
data.redis.publish('deploy', pickle.dumps(job_id))
def _fetch_and_parse(self, job_id, url, depth):
"""
Fetch a webpage and parse it for links and images.
Arguments:
job_id: intefer job id.
url: string URL.
depth: integer current depth.
Returns: None.
"""
html_parser = MyHtmlParser(url)
request_headers = {'User-Agent': self.user_agent}
request = urllib_Request(url, headers=request_headers)
try:
webpage = urlopen(request).read().decode()
except Exception as error:
data.redis.set(url, 'failed')
return
try:
html_parser.feed(webpage)
except (HTMLParseError) as error:
data.redis.set(url, 'failed')
return
data.add_webpages(url, html_parser.hyperlinks, depth)
data.redis.set(url, 'complete')
data.complete_crawl(url)
if 0 < depth and self._active and not data.job_is_aborted(job_id):
if html_parser.hyperlinks:
data.redis.sadd('job' + str(job_id), *html_parser.hyperlinks)
data.redis.publish('deploy', pickle.dumps(job_id))
from MyHtmlParser import MyHtmlParser
from sources import data
if __name__ == '__main__':
exclude = []
for k in data:
if k in exclude:
continue
for v in data[k]:
parsed = MyHtmlParser(dataset_name=v.get("dataset"),
url=v.get("url"),
dataset_type=k)
print(v.get('dataset'))
parsed.set_range_dates(v.get("period"))
parsed.retrieve_data()
import urllib.request
import urllib.parse
import urllib.error
import http.cookiejar
import html.parser
from MyHtmlParser import MyHtmlParser
url = 'http://www.esdict.cn/home/dailysentence'
headers = {"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:69.0) Gecko/20100101 Firefox/69.0"}
response = urllib.request.urlopen(url, timeout=10)
html = response.read().decode('utf-8')
htmlParser = MyHtmlParser()
htmlParser.feed(html)
data = htmlParser.HTMLData
htmlParser.clean()
for line in data:
if line[:4] == '每日一句':
print(line)