async def cb_sticker(event):
"To get list of sticker packs with given name."
split = event.pattern_match.group(1)
if not split:
return await edit_delete(event, "`Provide some name to search for pack.`", 5)
catevent = await edit_or_reply(event, "`Searching sticker packs....`")
scraper = cloudscraper.create_scraper()
text = scraper.get(combot_stickers_url + split).text
soup = bs(text, "lxml")
results = soup.find_all("div", {"class": "sticker-pack__header"})
if not results:
return await edit_delete(catevent, "`No results found :(.`", 5)
reply = f"**Sticker packs found for {split} are :**"
for pack in results:
if pack.button:
packtitle = (pack.find("div", "sticker-pack__title")).get_text()
packlink = (pack.a).get("href")
packid = (pack.button).get("data-popup")
reply += f"\n **• ID: **`{packid}`\n [{packtitle}]({packlink})"
await catevent.edit(reply)
def create_scrapper_session(useCloudscraper=True,
retries=10,
backoff_factor=0.3,
status_forcelist=(500, 502, 504, 423)):
session = None
if useCloudscraper:
session = cloudscraper.create_scraper()
else:
session = Session()
retry = Retry(
total=retries,
read=retries,
connect=retries,
backoff_factor=backoff_factor,
status_forcelist=status_forcelist,
)
adapter = HTTPAdapter(max_retries=retry)
session.mount('http://', adapter)
session.mount('https://', adapter)
return session
def test_user_agent(self, **kwargs):
for browser in ['chrome', 'firefox']:
scraper = cloudscraper.create_scraper(browser=browser)
assert browser in scraper.headers['User-Agent'].lower()
# Check it can't find browsers.json
with pytest.raises(RuntimeError,
match=r".*?User-Agent was not found\."):
scraper = cloudscraper.create_scraper(browser='bad_match')
# Check mobile and desktop disabled
with pytest.raises(
RuntimeError,
match=
r"Sorry you can't have mobile and desktop disabled at the same time\."
):
scraper = cloudscraper.create_scraper(browser={
'browser': 'chrome',
'desktop': False,
'mobile': False
})
# check brotli
scraper = cloudscraper.create_scraper(browser='chrome',
allow_brotli=False)
assert 'br' not in scraper.headers['Accept-Encoding']
# test custom User-Agent
scraper = cloudscraper.create_scraper(browser={'custom': 'test'})
assert scraper.headers['User-Agent'] == 'test'
# check its matched chrome and loaded correct cipherSuite
scraper = cloudscraper.create_scraper(browser={
'custom': '50.0.9370.394',
'tryMatchCustom': True
})
assert any('!' not in _ for _ in scraper.user_agent.cipherSuite)
# check it didn't match anything and loaded custom cipherSuite
scraper = cloudscraper.create_scraper(browser={
'custom': 'aa50.0.9370.394',
'tryMatchCustom': True
})
assert any('!' in _ for _ in scraper.user_agent.cipherSuite)
def query(self):
"""
向接口查询子域并做子域匹配
"""
time.sleep(self.delay)
# 绕过cloudFlare验证
scraper = cloudscraper.create_scraper()
scraper.interpreter = 'js2py'
scraper.proxies = self.get_proxy(self.source)
url = self.addr + self.domain
try:
resp = scraper.get(url, timeout=self.timeout)
except Exception as e:
logger.log('ERROR', e.args)
return
if not resp:
return
subdomains = self.match(self.domain, str(resp.json()))
# 合并搜索子域名搜索结果
self.subdomains = self.subdomains.union(subdomains)
def __init__(self, profileJson, _found):
self.profielPropeties = profileJson
self.found = _found
if _found:
self.cSession = cloudscraper.create_scraper()
self.display_name = profileJson["displayName"]
self.username = profileJson["username"]
self.bio = profileJson["aboutMe"]
self.avatar_url = profileJson["avatarFileName"]
self.user_id = profileJson["id"]
self.followersCount = profileJson["followerCount"]
self.anonymousFollowerCount = profileJson["anonymousFollowerCount"]
self.isFollowingcount = profileJson["followingCount"]
self.active = profileJson["isActive"]
self.tellsCount = profileJson["tellCount"]
self.tells = []
self.followers = []
self.followings = []
else:
return
def cb_sticker(update: Update, context: CallbackContext):
msg = update.effective_message
split = msg.text.split(" ", 1)
if len(split) == 1:
msg.reply_text("Provide some name to search for pack.")
return
scraper = cloudscraper.create_scraper()
text = scraper.get(combot_stickers_url + split[1]).text
soup = bs(text, "lxml")
results = soup.find_all("a", {"class": "sticker-pack__btn"})
titles = soup.find_all("div", "sticker-pack__title")
if not results:
msg.reply_text("No results found :(.")
return
reply = f"Stickers for *{split[1]}*:"
for result, title in zip(results, titles):
link = result["href"]
reply += f"\n• [{title.get_text()}]({link})"
msg.reply_text(reply, parse_mode=ParseMode.MARKDOWN)
def linkExtract():
target = input(
"[+] Target ( like https://google.com/ ) with http/https \t")
name = "links"
scraper = cloudscraper.create_scraper()
source = scraper.get(target).text
soup = BeautifulSoup(source, 'html.parser')
links = []
for link in soup.find_all(attrs={'href': re.compile("http")}):
links.append(link.get('href'))
for link in soup.find_all(attrs={'href': re.compile("https")}):
links.append(link.get('href'))
print("\n")
print(*set(links), sep="\n")
with open(home + "/webgather/" + name+"-links.txt", 'w+') as f:
for item in links:
f.write("%s\n" % item)
print(Fore.LIGHTMAGENTA_EX +
"\n [!] Found {0} links (some were duplicate). results Also saved in {1}/webgather/{2}-links.txt \n" .format(len(links), home, name))
input("")
recreate()
def bgDownloadAssets():
global config
scraper = cloudscraper.create_scraper()
apkPage = BeautifulSoup(scraper.get("https://apkpure.com/golf-blitz/com.noodlecake.ssg4/download").text, features="html.parser")
apkLink = apkPage.find("a", id="download_link")['href']
apkVersion = apkPage.find("span", attrs={"class": "file"}).text
if not "apkVersion" in config:
config["apkVersion"] = ""
if config["apkVersion"] != apkVersion:
print("downloading new apk for assets")
apkPath = os.path.join(bot_globals.resources_path, "golfblitz.apk")
with scraper.get(apkLink, stream=True) as dl: #requests.get(apkLink, stream=True)
with open(apkPath, "wb") as f:
for chunk in dl.iter_content(chunk_size=16384):
f.write(chunk)
with zipfile.ZipFile(apkPath, 'r') as to_unzip:
to_unzip.extractall(bot_globals.resources_path)
print("apk has been downloaded and extracted")
config["apkVersion"] = apkVersion
json.dump(config, open(os.path.join(confPath, "main-configuration.json"), 'w'))
bot_globals.update_hats_and_golfers()
def get_lab_urls(date):
''' returns all 4 lab urls from poelab.com
will return None for each if date on poelab doesnt match provided date (has not been updated yet)
date is format: %Y-%m-%d'''
labpages = []
ret = []
scraper = cloudscraper.create_scraper()
with scraper.get('https://www.poelab.com/') as r:
etree = lxmlhtml.fromstring(r.text)
labpages = etree.xpath('//h2/a[@class="redLink"]/@href')
for url in reversed(labpages[:4]):
with scraper.get(url) as r:
etree = lxmlhtml.fromstring(r.text)
t = etree.xpath('//img[@id="notesImg"]/@src')
if t:
t = t[0]
if date not in t:
ret.append(None)
else:
ret.append(t)
return ret
def __init__(
self,
language="English",
client_id="KzEZED7aC0vird8jWyHM38mXjNTY",
client_secret="W9JZoJe00qPvJsiyCGT3CCtC6ZUtdpKpzMbNlUGP",
):
self.language = language
self.client_id = client_id
self.client_secret = client_secret
self.account = None
self.access_token = None
self.refresh_token = None
# Using cloudscraper over a simple session allows us to
# get around Cloudflare.
self.session = cloudscraper.create_scraper()
self.session.headers.update(HEADERS)
if self.language: # pragma: no cover
self.session.headers.update({"Accept-Language": self.language})
def update_user_agents() -> None:
if not HAS_CF:
# The website with the UAs is behind Cloudflare's anti-bot page, we need cloudscraper
return
today = datetime.now()
ua_path = get_homedir() / 'user_agents' / str(today.year) / f'{today.month:02}'
safe_create_dir(ua_path)
ua_file_name: Path = ua_path / f'{today.date().isoformat()}.json'
if ua_file_name.exists():
# Already have a UA for that day.
return
try:
s = cloudscraper.create_scraper()
r = s.get('https://techblog.willshouse.com/2012/01/03/most-common-user-agents/')
except Exception:
traceback.print_exc()
return
to_store = ua_parser(r.text)
with open(ua_file_name, 'w') as f:
json.dump(to_store, f, indent=2)
def scrape(research_network: str):
ids = get_ids(research_network, 2272481)
data = get_existing_data(research_network)
completed_ids = set([d["id"] for d in data])
scraper = cloudscraper.create_scraper()
for id in tqdm(ids):
if id in completed_ids:
continue
url = f"https://papers.ssrn.com/sol3/papers.cfm?abstract_id={id}"
response = scraper.get(url)
save_abstract_data(research_network, {
"id": id,
"url": url,
"error": response.status_code != 200,
"status_code": response.status_code,
"html": remove_blank_space(response.text),
})
def anifo(URL):
URL = d_url(URL)
#URL = 'https://www.oploverz.in/series/one-piece-sub-indo/'
# scraper = cfscrape.create_scraper()
scraper = cloudscraper.create_scraper()
soup = BeautifulSoup(scraper.get(URL).content, 'html.parser')
desc = soup.find('span', class_='desc')
listinfo = soup.find('div', class_='listinfo')
img_des = soup.find('div', class_='imgdesc')
img = img_des.findChildren("img", recursive=False)
a = desc.prettify(formatter="html5")
b = listinfo.prettify(formatter="html5")
c = a.replace('"', "\"")
d = b.replace('"', "\"")
e = html.escape(c)
f = html.escape(d)
ret = {'desc': e, 'info': f, 'img': img[0]["src"]}
jsona = json.dumps(ret)
return jsona
def get_eps_list(URL):
URL = d_url(URL)
scraper = cloudscraper.create_scraper()
soup = BeautifulSoup(scraper.get(URL).content, 'html.parser')
episodelist = soup.find(class_='episodelist')
ret = []
for li in episodelist.find_all("li"):
eps = li.find(class_="leftoff")
judul = li.find(class_="lefttitle")
dt = li.find(class_="rightoff")
alink = eps.find("a")
con = {
'link': alink.get('href'),
'eps': eps.get_text().strip(),
'judul': judul.get_text().strip(),
'date': dt.get_text().strip()
}
ret.append(con)
return json.dumps(ret)
def get_jav_html(url_list: List[Union[int, str]]) -> str:
"""获取 javlibrary 网页内容；使用 cloudscraper 跳过 cloudflare 验证
:param url_list:[0]-errorTimes,[1]-url,[2]-proxy
:return: scraper.text
"""
scraper = cloudscraper.create_scraper(browser="chrome")
while url_list[0] != 6:
try:
rqs: Response = Response()
if len(url_list) == 2:
rqs = scraper.get(url_list[1])
elif len(url_list) == 3:
rqs = scraper.get(url_list[1], proxies=url_list[2])
rqs.encoding = 'utf-8'
return rqs.text
except Exception as e:
sleep(5)
if url_list[0] == 5:
raise e
url_list[0] += 1
def pixabay_index(request):
if not request.COOKIES.get('api'):
return redirect('pixabay_ask_api')
if request.method == 'GET':
query = request.GET.get('q')
if query:
return render(
request, 'stock_photos_explorer/pixabay-query.html', {
'title':
'Search Result for {} - Pixabay API Explorer'.format(
query).title(),
'theme':
'light'
})
image = bs(
cloudscraper.create_scraper().get('https://pixabay.com').content,
'lxml').find('picture').find('source')['srcset']
return render(request, 'stock_photos_explorer/pixabay-index.html', {
'title': 'Pixabay API Explorer',
'image': image
})
def scrape():
BASE_URL = "https://www.booksandcoupons.com/"
course_list = []
course_dict = {}
udemy_url = []
browser = {}
scraper = cloudscraper.create_scraper(browser)
# Creating a cloudscraper object so that will bypass any cloudscraper protection
try:
r = scraper.get(BASE_URL) ## base url
except:
raise ValueError("Fetching site error")
try:
soup = BS(r.text, "html.parser")
# Use beutifulsoup to pasre the html data extract information data.
header_courses = soup.find("h3", class_="post-title entry-title")
for i, tag in enumerate(header_courses):
course_list.insert(1, (tag.text, tag["href"]))
courses = soup.find_all("h3", class_="post-title entry-title")
for no, link in enumerate(courses):
course_link = link.find("a")
course_list.append((course_link.text, course_link["href"]))
except error:
print(error)
for i, j in dict((course_list)).items():
course_dict.setdefault(i, j)
for name, urls in course_dict.items():
r2 = scraper.get(urls)
if r2.status_code == 200:
soup2 = BS(r2.text, "html.parser")
tags2 = soup2.find_all("a", string="ENROLL NOW")
if len(tags2) == 1:
udemy_url.append((current_date, name, tags2[0]["href"]))
else:
udemy_url.append((current_date, name, tags2[1]["href"]))
return udemy_url
def main():
addseptag()
print('开始加载链接和代理...')
addseptag()
data, links, proxy = importLinkProxy()
proxyList = []
try:
proxyList = setupProxyFromUser(proxy)
except:
proxyList = setupProxyFromIp(proxy)
headers = {
'user-agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36',
}
with open('2captcha.txt') as f:
apiKey = f.read()
for i in range(len(links)):
scraper = cloudscraper.create_scraper(interpreter='nodejs',
recaptcha={
'provider': '2captcha',
'api_key': apiKey
})
try:
r = scraper.get(links[i],
headers=headers,
proxies=proxyList[i])
if r.status_code == 200 or r.status_code == 301:
print('激活成功')
status = '0'
outputToCsvStatus(i, status, data)
else:
print('激活失败')
status = '-1'
outputToCsvStatus(i, status, data)
except:
print('激活失败')
status = '-1'
outputToCsvStatus(i, status, data)
def __init__(self):
self._destroyed = False
self.executor = futures.ThreadPoolExecutor(max_workers=4)
# Initialize cloudscrapper
try:
self.scraper = cloudscraper.create_scraper(
browser={
'platform': 'linux',
'mobile': False
}
)
except Exception as err:
logger.exception('Failed to initialize cloudscraper')
self.scraper = Session()
# end try
# Must resolve these fields inside `read_novel_info`
self.novel_title = 'N/A'
self.novel_author = 'N/A'
self.novel_cover = None
self.is_rtl = False
# Each item must contain these keys:
# `id` - 1 based index of the volume
# `title` - the volume title (can be ignored)
self.volumes = []
# Each item must contain these keys:
# `id` - 1 based index of the chapter
# `title` - the title name
# `volume` - the volume id of this chapter
# `volume_title` - the volume title (can be ignored)
# `url` - the link where to download the chapter
self.chapters = []
# Other stuffs - not necessary to resolve from crawler instance.
self.home_url = ''
self.novel_url = ''
self.last_visited_url = None
def WaxWalletLogin(login, password, userToken2fa, captcha):
scraper = cloudscraper.create_scraper()
data = {
"password": password,
"username": login,
"g-recaptcha-response": captcha,
"redirectTo": ""
}
response = json.loads(
scraper.post("https://all-access.wax.io/api/session", data).text)
print(response)
data = {"code": Get2FA(userToken2fa), "token2fa": response["token2fa"]}
response = scraper.post("https://all-access.wax.io/api/session/2fa", data)
print(response.text)
response = scraper.get("https://all-access.wax.io/api/session")
print(response.text)
result = {"token": json.loads(response.text)["token"]}
print(result)
def xur_weapon():
scraper = cloudscraper.create_scraper(
delay=5, recaptcha={'provider': 'return_response'})
html = get_xur('https://whereisxur.com/')
soup = BeautifulSoup(html, 'html.parser')
xur_first_weapon = soup.find('div', class_="et_pb_blurb_0").find(
'h4', class_='et_pb_module_header').find('span').string
url_first_weapon = soup.find(
'div', class_="et_pb_blurb_0").find('noscript').find("img")["src"]
first_img = scraper.get(url_first_weapon, stream=True)
with open('xur_img/img_first_weapon.png', 'wb') as f:
f.write(first_img.content)
xur_second_weapon = soup.find('div', class_="et_pb_blurb_1").find(
'h4', class_='et_pb_module_header').find('span').string
url_second_weapon = soup.find(
'div', class_="et_pb_blurb_1").find('noscript').find("img")["src"]
second_img = scraper.get(url_second_weapon, stream=True)
with open('xur_img/img_second_weapon.png', 'wb') as f:
f.write(second_img.content)
xur_third_weapon = soup.find('div', class_="et_pb_blurb_2").find(
'h4', class_='et_pb_module_header').find('span').string
url_third_weapon = soup.find(
'div', class_="et_pb_blurb_2").find('noscript').find("img")["src"]
third_img = scraper.get(url_third_weapon, stream=True)
with open('xur_img/img_third_weapon.png', 'wb') as f:
f.write(third_img.content)
xur_fourth_weapon = soup.find('div', class_="et_pb_blurb_3").find(
'h4', class_='et_pb_module_header').find('span').string
url_fourth_weapon = soup.find(
'div', class_="et_pb_blurb_3").find('noscript').find("img")["src"]
fourth_img = scraper.get(url_fourth_weapon, stream=True)
with open('xur_img/img_fourth_weapon.png', 'wb') as f:
f.write(fourth_img.content)
save_xur_weapon(db, xur_first_weapon, xur_second_weapon, xur_third_weapon,
xur_fourth_weapon)
def fetch_course_data_by_class_id(self, class_id):
url = 'https://api.skillshare.com/classes/{}'.format(class_id)
scraper = cloudscraper.create_scraper(browser={
'custom':
'Skillshare/4.1.1; Android 5.1.1',
},
delay=10)
res = scraper.get(
url,
headers={
'Accept': 'application/vnd.skillshare.class+json;,version=0.8',
'User-Agent': 'Skillshare/5.3.0; Android 9.0.1',
'Host': 'api.skillshare.com',
'Referer': 'https://www.skillshare.com/',
'cookie': self.cookie,
})
if not res.status_code == 200:
raise Exception('Fetch error, code == {}'.format(res.status_code))
return res.json()
def on_task_input(self, task, config):
try:
import cloudscraper
except ImportError as e:
logger.debug('Error importing cloudscraper: {}', e)
raise plugin.DependencyError(
issued_by='cfscraper',
missing='cloudscraper',
message='CLOudscraper module required. ImportError: %s' % e,
)
scraper = cloudscraper.create_scraper()
category = config['category']
persistence = SimplePersistence(plugin='magnetdl')
last_magnet = persistence.get(category, None)
logger.debug('last_magnet: {}', last_magnet)
first_magnet = None
stop = False
for page in range(0, config['pages']):
logger.verbose('Retrieving {} page {}', category, page + 1)
url = self._url(category, page)
logger.debug('Url: {}', url)
try:
for entry in self.parse_page(scraper, url):
if first_magnet is None:
first_magnet = entry['url']
logger.debug('Set first_magnet to {}', first_magnet)
persistence[category] = first_magnet
if last_magnet == entry['url']:
logger.debug('Found page where we have left, stopping')
stop = True
yield entry
except Page404Error:
logger.warning('Page {} returned 404, stopping', page)
return
if stop:
return
time.sleep(random.randint(1, 5))
def json_download(self, chapter_id):
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36',
'Accept-Encoding': 'gzip, deflate'
}
sess = requests.session()
sess = cloudscraper.create_scraper(sess)
search_url = "http://www.mangaeden.com/api/manga/{0}/".format(chapter_id)
connection = sess.get(search_url, headers=headers)
if connection.status_code != 200:
print("Whoops! Seems like I can't connect to website.")
print("It's showing : %s" % connection)
print("Run this script with the --verbose argument and report the issue along with log file on Github.")
sys.exit(1)
else:
json_data = connection.content
return json_data
def _get_category(query):
url = "https://api.leboncoin.fr/api/parrot/v1/complete?q={query.replace(' ', '%20')}"
anti_captcha = create_scraper(browser="chrome")
res = anti_captcha.get(url).json()
print(type(res))
if res:
assert isinstance(
res, list), "Unexpected answer received from API: {res!r}"
return str(res[0]["cat_id"])
else:
# No category returned
return None
def update_user_agents():
if not HAS_CF:
# The website with the UAs is behind Cloudflare's anti-bot page, we need cloudscraper
return
today = datetime.now()
ua_path = get_homedir() / 'user_agents' / str(
today.year) / f'{today.month:02}'
safe_create_dir(ua_path)
ua_file_name: Path = ua_path / f'{today.date().isoformat()}.json'
if ua_file_name.exists():
# Already have a UA for that day.
return
try:
s = cloudscraper.create_scraper()
r = s.get(
'https://techblog.willshouse.com/2012/01/03/most-common-user-agents/'
)
except Exception:
traceback.print_exc()
return
soup = BeautifulSoup(r.text, 'html.parser')
uas = soup.find_all('textarea')[1].text
to_store = {'by_frequency': []}
for ua in json.loads(uas):
os = ua['system'].split(' ')[-1]
if os not in to_store:
to_store[os] = {}
browser = ' '.join(ua['system'].split(' ')[:-1])
if browser not in to_store[os]:
to_store[os][browser] = []
to_store[os][browser].append(ua['useragent'])
to_store['by_frequency'].append({
'os': os,
'browser': browser,
'useragent': ua['useragent']
})
with open(ua_file_name, 'w') as f:
json.dump(to_store, f, indent=2)
def update_addon(self, addon_name):
addon_link = self.config['addons'][addon_name]['link']
addon_last_update = self.config['addons'][addon_name]['last_update']
scraper = cloudscraper.create_scraper()
r = scraper.get(addon_link)
soup = BeautifulSoup(r.text, features='html.parser')
addon_name = soup.find("meta", property="og:title")["content"]
last_update = soup.find('abbr')['title']
converted_time = self.convert_datetime(last_update.split()[:4])
if converted_time > addon_last_update:
self.remove_addon(addon_name)
download_page = scraper.get(f'{addon_link}/download')
download_soup = BeautifulSoup(download_page.text,
features='html.parser')
link = download_soup.find('p', {
'class': 'text-sm'
}).find('a')['href']
download_link = f'http://www.curseforge.com{link}'
files = scraper.get(download_link)
existing_addons = os.listdir(self.addon_path)
with open(os.path.join(self.addon_path, 'addon.zip'), 'wb') as f:
f.write(files.content)
with ZipFile(os.path.join(self.addon_path, 'addon.zip'),
'r') as zipobj:
zipobj.extractall(self.addon_path)
os.remove(os.path.join(self.addon_path, 'addon.zip'))
all_addons = os.listdir(self.addon_path)
new_files = [x for x in all_addons if x not in existing_addons]
self.config['addons'][addon_name]['last_update'] = converted_time
self.config['addons'][addon_name]['files'] = new_files
self.save_config()
def create_novel(self):
try:
print("Initializing...")
scrapper = cloudscraper.create_scraper()
page = scrapper.get(self.novel_link)
soup = BeautifulSoup(page.text, 'html.parser')
# Get Novel Name
self.novel_name = soup.find(class_='title').get_text()
# Get the html that stores links to each chapter
chapters = soup.find_all(class_='rowChapter')
# Get all the specified links from the html
chapter_links = []
for chapter in chapters:
chapter_links.append(chapter.find('a').get('href'))
chapter_links.reverse() # Reverse the list so the first index will be the first chapter
print("Starting...")
book = EpubEngine(self.novel_name, self.storage_path)
book.addCover(self.storage_path + "/cover.png")
print("Added Cover")
current_chapter = 1
self.download_chapters(current_chapter, scrapper, chapter_links, book)
book.createEpub()
self.update_gui('END')
except Exception as e:
if 'Missing Node.js' in str(e):
self.update_gui("NODEJS")
else:
print(e)
self.update_gui('ERROR')
def Scrap_For_TOC(url):
"""scrapes the html for the ToC information"""
issue = ""
publication_type = ""
publication_info = []
scraper = cloudscraper.create_scraper()
web_text = scraper.get(url).text
soup = BeautifulSoup(web_text, features="lxml")
temp_soup = soup.get_text().replace('\n\n', '')
temp_soup = ''.join(temp_soup)
temp_soup = temp_soup.split('\n')
parsed_soup = []
start_stop_parsing = 0
start_stop_pub_info = 0
#x=0
for line in temp_soup: #soup.get_text():
#print(line)
if 'Facebook pageRSS FeedsMost recent' in line:
start_stop_parsing = 1
#print("start_stop = 1")
elif 'ToolsSubmit an Article' in line:
start_stop_parsing = 0
#print("start_stop = 0")
if start_stop_parsing == 1:
parsed_soup.append(str(line))
#print(line)
if 'Select / Deselect allExport Citation(s)Export' in line:
issue = line
if 'Open Access' in line:
start_stop_pub_info = 1
elif 'Full text' in line:
start_stop_pub_info = 0
if start_stop_pub_info == 1 and start_stop_parsing == 1:
publication_info.append(line)
#x += 1
print(issue)
print(publication_info)
def gethtml(url, req='', headers='', interpreter='nodejs'):
# session = requests.session()
# session = cfscrape.create_scraper()
session = cloudscraper.create_scraper(interpreter=interpreter)
session.mount('file://', LocalFileAdapter())
cookies_ = ConfigParser()
cookies_.read('cookies')
session.cookies['sess_id'] = cookies_.get('COOKIES', 'sess_id')
session.cookies['session_id'] = cookies_.get('COOKIES', 'sess_id')
#lang, lang2, forcesub, forceusa, localizecookies, quality, onlymainsub, connection_n_, proxy_ = config()
config_ = config()
if config_['forceusa']:
session.cookies['sess_id'] = cookies_.get('COOKIES', 'sess_id_usa')
session.cookies['session_id'] = cookies_.get('COOKIES', 'sess_id_usa')
del session.cookies['c_visitor']
if not config_['forceusa'] and config_['localizecookies']:
session.cookies['c_locale'] = \
{u'Español (Espana)': 'esES', u'Français (France)': 'frFR', u'Português (Brasil)': 'ptBR',
u'English': 'enUS', u'Español': 'esLA', u'Türkçe': 'enUS', u'Italiano': 'itIT',
u'العربية': 'arME', u'Deutsch': 'deDE', u'Русский': 'ruRU'}[config_['language']]
if not urlparse(url).scheme and not urlparse(url).netloc:
print('Apparently not a URL')
sys.exit()
if headers == '':
headers = {
'Referer':
'http://crunchyroll.com/',
'Host':
'www.crunchyroll.com',
'User-Agent':
'Mozilla/5.0 Windows NT 6.1; rv:26.0 Gecko/20100101 Firefox/26.0'
}
res = session.get(url, params=req, headers=headers)
res.encoding = 'UTF-8'
#print(session.get(url, params=req, headers=headers).url)
#open('page.html', 'a',encoding='UTF-8').write(res.text)
return res.text
