def timetable_for_film(film):
timetable_list = []
times = driver.find_elements_by_xpath("//*[@id='%s']/tbody/tr/td[2]/div" %
film) # ПОЛУЧЕНИЕ ВРЕМЕНИ ФИЛЬМА
for time in times:
timetable_list.append(time.get_attribute("innerHTML"))
cinemas_list = []
cinemas = driver.find_elements_by_xpath(
"//*[@id='%s']/tbody/tr/td[1]/a" % film) # ПОЛУЧЕНИЕ КИНОТЕАТРА ФИЛЬМА
for cinema in cinemas:
cinemas_list.append(cinema.text)
return tuple(zip(timetable_list, cinemas_list))
def post_commenter(user_id):
directory = USER_DIR + user_id + "/"
postLinkFile = directory + 'PostLink.csv'
driver = webdriver.Firefox()
driver.implicitly_wait(10)
myFile = open(directory + 'Commenters.csv', 'wb')
textWriter = csv.writer(myFile)
textWriter.writerow(
["index", "url", "time", "like", "interaction", "commenter"])
with open(postLinkFile, 'rb') as csvfile:
spamreader = csv.reader(csvfile)
next(spamreader, None) # skip the headers
for row in spamreader:
driver.get(row[1])
try:
time = driver.find_element_by_class_name('_379kp')
like = driver.find_element_by_class_name('_tf9x3')
likeNum = like.find_element_by_css_selector(
'span').get_attribute('innerHTML')
listOfCommenters = ""
try:
interaction = 0
comments = driver.find_elements_by_css_selector(
'._4zhc5.notranslate._iqaka')
interaction = len(comments)
commenters = []
commenters_counts = {}
for comment in comments:
commenters.append(comment.get_attribute('title'))
commenters_counts = Counter(commenters)
for item in commenters_counts.items():
listOfCommenters = listOfCommenters + item[
0] + ":" + str(item[1]) + ","
except NoSuchElementException:
listOfCommenters = "0"
except NoSuchElementException:
likeNum = 0
finally:
time = time.get_attribute('datetime')
textWriter.writerow([
row[0], row[1], time, likeNum, interaction,
listOfCommenters
])
myFile.flush()
def get_date_time(self):
month = self.driver.find_element_by_xpath(
'//*[@id="game__top__inner"]/div[1]/p[2]/span')
week = self.driver.find_element_by_xpath(
'//*[@id="game__top__inner"]/div[1]/p[3]/span[1]')
time = self.driver.find_element_by_xpath(
'//*[@id="game__top__inner"]/div[1]/p[4]')
cell_list = self.ws.range('A3:C3')
m_w_t = [
month.get_attribute("textContent"),
week.get_attribute("textContent"),
time.get_attribute("textContent")
]
for i, cell in enumerate(cell_list):
val = m_w_t[i]
cell.value = val
self.ws.update_cells(cell_list, value_input_option='USER_ENTERED')
def get_latest_tweet():
driver.get(TWITTER_URL)
tweets_xpath = '//*[@data-testid="tweet"]'
elements = None
try:
elements = WebDriverWait(driver, 15).until(
EC.visibility_of_all_elements_located((By.XPATH, tweets_xpath)))
except TimeoutException as e:
# tweets are not visible in some rare cases, return empty string instead
return None
finally:
# getting latest tweet
latest_tweet = None
latest_tweet_timestamp = None
if elements is not None:
for tweet in elements:
time = tweet.find_element_by_xpath(".//time")
timestamp = time.get_attribute("datetime")
date = datetime.datetime.strptime(timestamp,
'%Y-%m-%dT%H:%M:%S.000Z')
if latest_tweet_timestamp is None or date > latest_tweet_timestamp:
latest_tweet_timestamp = date
latest_tweet = tweet
latest_tweet_text_formatted = "".join(
latest_tweet.text.split("\n")[4:-3])
return {
"text": latest_tweet_text_formatted,
"date": latest_tweet_timestamp
}
return None
def traffic(config):
options = se.webdriver.ChromeOptions()
options.add_argument('headless')
driver = se.webdriver.Chrome(chrome_options=options)
home = config['home']
destination = config['destination']
url = 'https://www.google.com/maps/dir/' + home + ',' + destination + '/@37.3806044,-122.0178939,12z/data=!3m1!4b1!4m14!4m13!1m5!1m1!1s0x808fcc3e5f95acc3:0x47daf6fd38218ca4!2m2!1d-121.8762513!2d37.3853429!1m5!1m1!1s0x808fb64142d26eaf:0x8192e11989e6e62f!2m2!1d-122.020508!2d37.380601!3e0'
#url = 'https://www.google.com/maps/dir/'+home+','+destination+'/@37.3806044,-122.0178939,12z/data=!3m1!4b1!4m14!4m13!1m5!1m1!1s0x808fcc3e5f95acc3:0x47daf6fd38218ca4!2m2!1d-121.8762513!2d37.3853429!1m5!1m1!1s0x808fb64142d26eaf:0x8192e11989e6e62f!2m2!1d-122.020508!2d37.380601!3e0'
urlTest = 'https://www.google.com/maps/dir/' + home + ',' + destination + '/@37.3806044,-122.0178939,12z/data=!3m1!4b1!4m18!4m17!1m5!1m1!1s0x808fcc3e5f95acc3:0x47daf6fd38218ca4!2m2!1d-121.8762513!2d37.3853429!1m5!1m1!1s0x808fb64142d26eaf:0x8192e11989e6e62f!2m2!1d-122.020508!2d37.380601!2m3!6e0!7e2!8j1545897900!3e0'
driver.get(url)
time = driver.find_element(
By.XPATH, '//div[@class="section-directions-trip-numbers"]/div')
distance = driver.find_element(
By.XPATH,
'//div[@class="section-directions-trip-numbers"]/div[@class="section-directions-trip-distance section-directions-trip-secondary-text"]'
)
crowd = time.get_attribute("class").split("delay-")[1]
strOutput = "Traffic: " + crowd + '\n' + "Time: " + time.text + '\n' + distance.text + '\n'
if crowd == 'heavy':
strOutput = strOutput + "太堵啦，要不等会儿再出发"
print(strOutput)
config['cache']['traffic'] = strOutput
with open("config.json", "w") as jsonFile:
json.dump(config, jsonFile, indent=4)
def getScheduledMatches(code, year, url):
driver.get(url)
loadAll()
print(code)
tbody = driver.find_element_by_css_selector('.sportName')
matches = tbody.find_elements_by_xpath('*')
roundmatches = {}
round = ""
id = 12
formermonth = 1
year += 2
for match in matches:
if hasClass(match, "event__round"):
round = match.get_attribute('innerText')
print(round)
if len(match.find_elements_by_css_selector(
'.event__participant--home')) != 0:
roundmatches[id] = []
home = match.find_element_by_css_selector(
'.event__participant--home')
away = match.find_element_by_css_selector(
'.event__participant--away')
score = match.find_element_by_css_selector('.event__scores')
r = score.find_elements_by_css_selector('span')
time = match.find_element_by_css_selector('.event__time')
time.__setattr__('year', year)
print(year)
time = datetime.strptime(
time.get_attribute('innerHTML') + ' ' + str(year),
'%d.%m. %H:%M %Y')
if time.month > formermonth:
year -= 1
formermonth = time.month
time = datetime(year, time.month, time.day, time.hour, time.minute)
homescore = r[0].get_attribute('innerText')
awayscore = r[1].get_attribute('innerText')
hometeamname = re.findall("\w+", home.get_attribute('innerText'))
awayteamname = re.findall("\w+", away.get_attribute('innerText'))
hometeamname = (' '.join(hometeamname))
awayteamname = (' '.join(awayteamname))
# print (home.find_element_by_xpath('span').get_attribute('innerText')+"-"+ away.find_element_by_xpath('span').get_attribute('innerText') + " "+homescore + ":" + awayscore)
roundmatches[id] = (match1(hometeamname, awayteamname, time,
homescore, awayscore, round))
id += 1
# print(roundmatches)
formermonth = time.month
roundmatches = sorted(roundmatches.items(),
key=operator.itemgetter(0),
reverse=True)
B = []
C = []
F = []
G = []
H = []
I = []
D = []
E = []
for i in roundmatches:
F.append(getattr(i[1], 'hometeam'))
G.append(getattr(i[1], 'awayteam'))
H.append(int(getattr(i[1], 'homescore')))
I.append(int(getattr(i[1], 'awayscore')))
timematch = getattr(i[1], 'date')
E.append(datetime.time(timematch))
D.append(datetime.date(timematch))
B.append("")
C.append(timematch.year)
print(F)
print(G)
print(H)
print(I)
df = pd.DataFrame({
'B': B,
'C': C,
'D': D,
'E': E,
'F': F,
'G': G,
'H': H,
'I': I
})
writer = pd.ExcelWriter('C:\\Users\\danida\\Desktop\\excels2\\' + code +
'.xls',
engine='xlwt')
df.to_excel(writer, sheet_name='Sheet1')
# Close the Pandas Excel writer and output the Excel file.
writer.save()
print(roundmatches)
#for reply in replies:
# repliess.append(reply.text)
repliess_1 = [reply.text for reply in replies_1]
#for retweet in retweets:
# retweetss.append(retweet.text)
retweetss_1 = [retweet.text for retweet in retweets_1]
#for like in likes:
# likess.append(like.text)
likess_1 = [like.text for like in likes_1]
#for time in times:
# timess.append(time.get_attribute("title"))
timess_1 = [time.get_attribute("title") for time in times_1]
#for perma in permas:
# permass.append(perma.text)
#for hash_tag in hash_tags:
# print (hash_tag.text)
#<strong class="fullname show-popup-with-id u-textTruncate " data-aria-label-part="">TekNotice</strong>
#<span class="username u-dir u-textTruncate" dir="ltr" data-aria-label-part="">@<b>TekNotice</b></span>
#<a href="/TekNotice/status/952962598311313408" class="tweet-timestamp js-permalink js-nav js-tooltip" title="6:56 PM - 15 Jan 2018" data-conversation-id="952962598311313408"><span class="_timestamp js-short-timestamp js-relative-timestamp" data-time="1516038963" data-time-ms="1516038963000" data-long-form="true" aria-hidden="true">2h</span><span class="u-hiddenVisually" data-aria-label-part="last">2 hours ago</span></a>
#<a href="/hashtag/samsungs8?src=hash" data-query-source="hashtag_click" class="twitter-hashtag pretty-link js-nav" dir="ltr"><s>#</s><b><strong>samsungs8</strong></b></a>
#<span class="ProfileTweet-actionCountForAria" id="profile-tweet-action-reply-count-aria-952962598311313408">0 replies</span>
#for tweet in tweets:
# print(tweet.text)
