def main():
source = requests.get('http://goodyfoodies.blogspot.com').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find_all('div',
class_='post hentry uncustomized-post-template')
for article in articles:
headline = article.h3.text
summary = article.find('div', class_='post-body entry-content').text
commentLink = article.find('span',
class_='post-comment-link').a['href']
commentSource = requests.get(commentLink).text
commentSoup = BeautifulSoup(commentSource, 'lxml')
comments = commentSoup.find_all('div', class_='comment-block')
id = 0
commList = []
for comment in comments:
id = id + 1
refid = 1
user = comment.div.cite.text
date = comment.find('span',
class_='datetime secondary-text').a.text
parsed_date = parse(date)
# print('Date:', parsed_date.date())
# print('time:', parsed_date.time())
timestamp = datetime.datetime.timestamp(parsed_date)
# print(timestamp)
msg = comment.p.text
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)
def main():
source = requests.get('http://journeyofanitaliancook.blogspot.com/').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find_all('div', class_='post hentry')
for article in articles:
headline = article.h3.text
summary = article.find('div', class_='post-body entry-content').text
commentLink = article.find('span', class_='post-comment-link').a['href']
commentSource = requests.get(commentLink).text
commentSoup = BeautifulSoup(commentSource, 'lxml')
comments = commentSoup.find_all('dl', id='comments-block')
id = 0
commList = []
for comment in comments:
id = id + 1
refid = 1
user = comment.dt.span.text
date = comment.find('p', class_='comment-timestamp').text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = comment.dd.p.text
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)
def main():
source = requests.get('http://theworldaccordingtoeggface.blogspot.com/').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find_all('div', class_='post hentry')
for article in articles:
headline = article.h3.text
summary = article.find('div', class_='post-body entry-content').text
commentLink = article.h3.a['href'] #este link-ul din headline pentru ca nu exista nicio referinta la comentarii in pagina home
commentSource = requests.get(commentLink).text
commentSoup = BeautifulSoup(commentSource, 'lxml')
# comments = commentSoup.find('div', class_='comments')
# nu exista niciun comentariu pe acest blog
posts.append(Post(headline, summary, ""))
for post in posts:
print(post)
def main():
source = requests.get('https://mainlymacro.blogspot.com/').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find_all('div',
class_='post hentry uncustomized-post-template')
for article in articles:
headline = article.h3.a.text
summarySource = requests.get(article.h3.a['href']).text
summarySoup = BeautifulSoup(summarySource, 'lxml')
summaryList = summarySoup.find(
'div', class_='post-body entry-content').find_all('span')
summary = ""
for s in summaryList:
summary = summary + " " + s.text.replace('\n', '').replace(
'\t', '')
try:
comments = summarySoup.find('ol', id='top-ra').find_all('li')
except Exception as e:
comments = []
id = 0
commList = []
anonymous = 1
for comment in comments:
id = id + 1
refid = 1
user = comment.find('div',
class_='comment-header').cite.text.replace(
'\n', '').replace('\t', '')
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = comment.find('span',
class_='datetime secondary-text').text.replace(
'\n', '').replace('\t', '')
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = comment.find('p', class_='comment-content').text.replace(
'\n', '').replace('\t', '')
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = True
while fail_condition:
try:
replies = comment.find(
'div', class_='comment-replies').find_all('li')
refid = id
for reply in replies:
id = id + 1
user = reply.find(
'div', class_='comment-header').cite.text.replace(
'\n', '').replace('\t', '')
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = reply.find(
'span',
class_='datetime secondary-text').text.replace(
'\n', '').replace('\t', '')
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = reply.find(
'p', class_='comment-content').text.replace(
'\n', '').replace('\t', '')
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = False
except Exception as e:
fail_condition = False
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)
def main():
source = requests.get('https://www.honeywerehome.com/').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find_all('div', class_='entry-summary')
for article in articles:
headline = article.div.a['title']
summaryList = article.find_all('p')
summary = ""
for s in summaryList:
summary = summary + " " + s.text
commentLink = article.a['href']
commentSource = requests.get(commentLink).text
commentSoup = BeautifulSoup(commentSource, 'lxml')
comments = commentSoup.find('ol', class_='comment-list').find_all('li')
id = 0
commList = []
for comment in comments:
id = id + 1
refid = 1
user = comment.find('div', class_='comment-author').cite.text
date = comment.find('span', class_='comment-date').text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = comment.find('div', class_='comment-content').p.text
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = True
while fail_condition:
try:
replies = comment.find('ul',
class_='children').find_all('li')
refid = id
for reply in replies:
id = id + 1
user = reply.find('div',
class_='comment-author').cite.text
date = reply.find('span', class_='comment-date').text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = reply.find('div',
class_='comment-content').p.text
print(user)
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = False
except Exception as e:
fail_condition = False
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)
def main():
source = requests.get('https://thinkmarkets.wordpress.com').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find_all('article')
for article in articles:
headline = article.header.h1.a.text
summarySource = requests.get(article.header.h1.a['href']).text
summarySoup = BeautifulSoup(summarySource, 'lxml')
summaryList = summarySoup.find('div',
class_='entry-content').find_all('p')
summary = ""
for s in summaryList:
summary = summary + " " + s.text.replace('\n', '').replace(
'\t', '')
try:
comments = summarySoup.find('ol',
class_='comment-list').find_all('li')
except Exception as e:
comments = []
id = 0
commList = []
anonymous = 1
for comment in comments:
id = id + 1
refid = 1
user = comment.find('div',
class_='comment-author vcard').b.text.replace(
'\n', '').replace('\t', '')
if user == '':
user = comment.find(
'div', class_='comment-author vcard').b.a.text.replace(
'\n', '').replace('\t', '')
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = comment.find('div',
class_='comment-metadata').a.time.text.replace(
'\n', '').replace('\t', '')
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = ""
msgList = comment.find('div',
class_='comment-content').find_all('p')
for m in msgList:
msg = msg + m.text.replace('\n', '').replace('\t', '')
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = True
while fail_condition:
try:
replies = comment.find('ul',
class_='children').find_all('li')
refid = id
for reply in replies:
id = id + 1
user = reply.find(
'div',
class_='comment-author vcard').b.text.replace(
'\n', '').replace('\t', '')
if user == '':
user = reply.find('div',
class_='comment-author vcard'
).b.a.text.replace('\n',
'').replace(
'\t', '')
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = reply.find(
'div',
class_='comment-metadata').a.time.text.replace(
'\n', '').replace('\t', '')
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = ""
msgList = reply.find(
'div', class_='comment-content').find_all('p')
for m in msgList:
msg = msg + m.text.replace('\n', '').replace(
'\t', '')
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = False
except Exception as e:
fail_condition = False
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)
def main():
source = requests.get('http://warnewsupdates.blogspot.com/').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find('div',
class_='widget Blog').find_all('div',
class_='post hentry')
for article in articles:
headline = article.h3.a.text
summarySource = requests.get(article.h3.a['href']).text
summarySoup = BeautifulSoup(summarySource, 'lxml')
summary = summarySoup.find('div',
class_='post-body entry-content').text
summary = summary.replace('\n', "")
# print(summary)
try:
comments = summarySoup.find('ol',
class_='commentlist').find_all('li')
except Exception as e:
comments = []
id = 0
commList = []
anonymous = 1
for comment in comments:
id = id + 1
refid = 1
user = comment.find('div', class_='comment-author vcard').cite.text
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = comment.find('div',
class_='comment-meta commentmetadata').a.text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = ""
msgList = comment.find('div', class_='comment-body').find_all('p')
for m in msgList:
if 'Like' not in m.text:
msg = msg + m.text + " "
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = True
while fail_condition:
try:
replies = comment.find('ul',
class_='children').find_all('li')
refid = id
for reply in replies:
id = id + 1
user = reply.find(
'div', class_='comment-author vcard').cite.text
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = reply.find(
'div',
class_='comment-meta commentmetadata').a.text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = ""
msgList = reply.find(
'div', class_='comment-body').find_all('p')
for m in msgList:
if m.text != 'Like':
if 'Like' not in m.text:
msg = msg + m.text + " "
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = False
except Exception as e:
fail_condition = False
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)
def main():
source = requests.get('http://2politicaljunkies.blogspot.com/').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find_all('div', class_='post hentry')
for article in articles:
headline = article.h3.a.text
summarySource = requests.get(article.h3.a['href']).text
summarySoup = BeautifulSoup(summarySource, 'lxml')
summary = summarySoup.find(
'div', class_='post-body entry-content').text.replace('\n', '')
try:
commentUsers = summarySoup.find('div', id='comments').find_all(
'dt', class_='comment-author')
commentBodies = summarySoup.find('div', id='comments').find_all(
'dd', class_='comment-body')
commentFooters = summarySoup.find('div', id='comments').find_all(
'dd', class_='comment-footer')
except Exception as e:
comments = []
id = 0
commList = []
anonymous = 1
for comment in commentBodies:
id = id + 1
refid = 1
commentUser = commentUsers.pop(0)
user = commentUser.text.replace('said...', '').replace('\n', '')
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
commentFooter = commentFooters.pop(0)
date = commentFooter.find('span',
class_='comment-timestamp').a.text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
try:
msg = comment.find('p').text.replace('\n', ' ')
except Exception as e:
msg = ''
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)
def main():
source = requests.get('http://inspiringscience.net').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find('div', id='content').find_all('article')
for article in articles:
headline = article.header.h1.a.text
summarySource = requests.get(article.header.h1.a['href']).text
summarySoup = BeautifulSoup(summarySource, 'lxml')
summaryList = summarySoup.find('div',
class_='post-entry').find_all('p')
summary = ""
for s in summaryList:
summary = summary + " " + s.text
try:
comments = summarySoup.find('ol',
class_='commentlist').find_all('li')
except Exception as e:
comments = []
id = 0
commList = []
anonymous = 1
for comment in comments:
id = id + 1
refid = 1
user = comment.find('p', class_='comment-author').span.text
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = comment.find('p', class_='comment-date').a.time.text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = ''
msgList = comment.find('div', class_='comment-text').find_all('p')
del msgList[-1]
for m in msgList:
msg = msg + m.text + " "
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = True
while fail_condition:
try:
replies = comment.find('ul',
class_='children').find_all('li')
refid = id
for reply in replies:
id = id + 1
user = reply.find('p',
class_='comment-author').span.text
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = reply.find('p',
class_='comment-date').a.time.text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = ''
msgList = reply.find(
'div', class_='comment-text').find_all('p')
del msgList[-1]
for m in msgList:
msg = msg + m.text + " "
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = False
except Exception as e:
fail_condition = False
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)
def main():
source = requests.get('https://fullymyelinated.wordpress.com/').text
soup = BeautifulSoup(source, 'lxml')
posts = []
articles = soup.find('div', id='content-left').find_all('div',
class_='entry')
for article in articles:
headline = article.h2.a.text
summarySource = requests.get(article.h2.a['href']).text
summarySoup = BeautifulSoup(summarySource, 'lxml')
summary = ""
summaryList = summarySoup.find('div', class_='entry').find_all('p')
summaryList.pop(0) #remove 'leave a comment' text
for s in summaryList:
summary = summary + s.text.replace('\n', '')
try:
comments = summarySoup.find(
'ol', class_='commentlist snap_preview').find_all('li')
except Exception as e:
comments = []
id = 0
commList = []
anonymous = 1
for comment in comments:
id = id + 1
refid = 1
try:
user = comment.find('div',
class_='comment-author vcard').cite.text
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = comment.find(
'div', class_='comment-meta commentmetadata').a.text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = ""
msgList = comment.find('div',
class_='comment-body').find_all('p')
for m in msgList:
msg = msg + m.text.replace('\n', '') + ' '
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
except Exception as e:
comm = None
fail_condition = True
while fail_condition:
try:
replies = comment.find('ul',
class_='children').find_all('li')
refid = id
for reply in replies:
id = id + 1
user = reply.find(
'div', class_='comment-author vcard').cite.text
if user == 'Unknown' or user == 'Anonymous':
user = '******' + str(anonymous)
anonymous = anonymous + 1
date = reply.find(
'div',
class_='comment-meta commentmetadata').a.text
parsed_date = parse(date)
timestamp = datetime.datetime.timestamp(parsed_date)
msg = ""
msgList = reply.find(
'div', class_='comment-body').find_all('p')
for m in msgList:
msg = msg + m.text.replace('\n', '') + ' '
comm = Comment(id, refid, timestamp, user, msg)
commList.append(comm)
fail_condition = False
except Exception as e:
fail_condition = False
posts.append(Post(headline, summary, commList))
for post in posts:
print(post)