Just Scraping Alpha

This commit is contained in:
Rumps 2017-01-13 17:56:41 +00:00
parent 75e3dc5790
commit b6c1660f04
24 changed files with 8 additions and 1000 deletions

View file

@ -1,16 +1,16 @@
# Scraping Alpha # Scraping Alpha
### Author ## Author
Ben Goldsworthy Ben Goldsworthy
<[email](mailto:b.goldsworthy@lancaster.ac.uk)> <[email](mailto:b.goldsworthy@lancaster.ac.uk)>
<[website](http://www.bengoldsworthy.uk/)> <[website](http://www.bengoldsworthy.uk/)>
### Version ## Version
1.0 1.0
### Abstract ## Abstract
Scraping Alpha is a series of Python scripts used to scrape Scraping Alpha is a series of Python scripts used to scrape
[Seeking Alpha](http://seekingalpha.com/) earnings call transcripts and produce [Seeking Alpha](http://seekingalpha.com/) earnings call transcripts and produce
@ -18,13 +18,13 @@ SQL from them.
It was created for Dr Lars Hass of the Lancaster University Management School. It was created for Dr Lars Hass of the Lancaster University Management School.
### Usage ## Usage
The instructions for each step of the process can be found at the beginning of The instructions for each step of the process can be found at the beginning of
each of the files involved: `transcript_spider.py`, `JSONtoSQL.py` and each of the files involved: `transcript_spider.py`, `JSONtoSQL.py` and
`execsAndAnalysts.py`. The are repeated here for brevity. `execsAndAnalysts.py`. The are repeated here for brevity.
#### `transcript_spider.py` ### `transcript_spider.py`
This file is the webspider that Scrapy uses to retrieve the information from the This file is the webspider that Scrapy uses to retrieve the information from the
website. Left unattended, it will scrape all 4,000+ pages of results. website. Left unattended, it will scrape all 4,000+ pages of results.
@ -54,7 +54,7 @@ For installation instructions for Scrapy, see
transcripts -o transcripts.json` at the command line (the output file will be transcripts -o transcripts.json` at the command line (the output file will be
placed in the directory the Terminal is currently pointing to). placed in the directory the Terminal is currently pointing to).
#### `JSONtoSQL.py` ### `JSONtoSQL.py`
This file takes the `transcripts.json` file output of `transcript_spider.py` and This file takes the `transcripts.json` file output of `transcript_spider.py` and
converts it into SQL. converts it into SQL.
@ -63,7 +63,7 @@ This file should be located in the same directory as `transcripts.json`, and is
run via `python JSONtoSQL.py > [FILE].sql`, where `[FILE]` is the desired name run via `python JSONtoSQL.py > [FILE].sql`, where `[FILE]` is the desired name
of the output file. of the output file.
#### `execsAndAnalysts.py` ### `execsAndAnalysts.py`
First, import the output file of `JSONtoSQL.py` to your chosen DBMS (I've tested First, import the output file of `JSONtoSQL.py` to your chosen DBMS (I've tested
it with phpMyAdmin). Then, run the following query: it with phpMyAdmin). Then, run the following query:
@ -80,6 +80,6 @@ into your DBMS to create two linking tables. The final instruction of
`analysts.sql` then deletes the superfluous `execs` and `analysts` columns from `analysts.sql` then deletes the superfluous `execs` and `analysts` columns from
the `transcripts` table (and for this reason, `execs.sql` must be imported first). the `transcripts` table (and for this reason, `execs.sql` must be imported first).
### Future ## Future
Harvesting the URLs of slide images shouldn't be too hard to implement - `slides_spider.py` should in theory to this, but the link to a transcript's slides is added to the page later via Javascript, which means at the moment it throws up a load of HTTP 200 status codes and nowt else. [Scrapy+Splash](https://github.com/scrapy-plugins/scrapy-splash) may be the solution, however. Harvesting the URLs of slide images shouldn't be too hard to implement - `slides_spider.py` should in theory to this, but the link to a transcript's slides is added to the page later via Javascript, which means at the moment it throws up a load of HTTP 200 status codes and nowt else. [Scrapy+Splash](https://github.com/scrapy-plugins/scrapy-splash) may be the solution, however.

View file

@ -1,27 +0,0 @@
# PatentSlurp
Patent slurper for Dr Lars Hass, LUMS
# TODO
1) Add stripper for redundant xml tags
2) Harvest below data from Google dumps 2001-2015:
-------------------------------------------------------------------------------
storage display value
variable name type format label variable label
-------------------------------------------------------------------------------
sta str2 %2s assg/state
cnt str3 %3s assg/country
assgnum byte %8.0g assg/assignee seq. number (imc)
cty str72 %72s assg/city
pdpass long %12.0g Unique assignee number
ptype str1 %9s patent type
patnum long %12.0g patent number
-------------------------------------------------------------------------------
3) Compare data with NBER data (http://eml.berkeley.edu/~bhhall/NBER06.html)
4) ...
# Useful Tools
http://codebeautify.org/xmlviewer
http://www.regexr.com/

View file

@ -1,183 +0,0 @@
#!/usr/bin/env perl
use 5.010;
#use strict;
use warnings;
use XML::Simple;
use XML::Twig;
use Time::Piece;
=pod
=head1 NAME
PATENT_SLURPER - A program to process Google/USPTO data dumps
=head1 VERSION
0.8
=head1 DESCRIPTION
This program takes L<Google/USPTO data dumps|https://www.google.com/googlebooks/uspto-patents-grants-text.html>
and produces SQL commands to generate a database from them with a
number of selected fields.
=head1 AUTHOR
L<Ben Goldsworthy (rumperuu)|mailto:b.goldsworthy96@gmail.com>
=head1 LICENSE
=cut
# Trims the file extension from the filename argument
my $filename = $ARGV[0];
chomp $filename;
my $patentTwig = new XML::Twig(TwigRoots => {
'SDOBI/B100/B140/DATE/PDAT' => 1,
'SDOBI/B100/B110/DNUM/PDAT' => 2,
'SDOBI/B200/B220/DATE/PDAT' => 3,
'SDOBI/B200/B210/DNUM/PDAT' => 4
},
TwigHandlers => {
'SDOBI/B100/B140/DATE/PDAT' => sub { $_->set_tag( 'appdate') },
'SDOBI/B100/B110/DNUM/PDAT' => sub { $_->set_tag( 'appnum') },
'SDOBI/B200/B220/DATE/PDAT' => sub { $_->set_tag( 'pubdate') },
'SDOBI/B200/B210/DNUM/PDAT' => sub { $_->set_tag( 'pubnum') }
},
pretty_print => 'indented');
my $citationTwig = new XML::Twig(TwigRoots => {
'SDOBI/B200/B210/DNUM/PDAT' => 1,
'SDOBI/B500/B560/B561/PCIT/DOC/DNUM/PDAT' => 2
},
TwigHandlers => {
'SDOBI/B200/B210/DNUM/PDAT' => sub { $_->set_tag( 'pubnum') },
'SDOBI/B500/B560/B561/PCIT/DOC/DNUM/PDAT' => sub { $_->set_tag('citing') }
},
pretty_print => 'indented');
my $numLines = countFile($filename);
print "Processing $numLines lines...\n";
processFile($filename, $numLines);
print "File processing finished - press '1' to generate SQL statements, or '0' to quit.\n";
while (1) {
given (<STDIN>) {
when(1) {
generateSQL($filename);
print "SQL generation finished.\n";
exit 0;
} when(0) {
exit 0;
} default {
print "Press '1' to generate SQL statements, or '0' to quit.\n";
}
};
}
# Goes through the file serially to count the lines
sub countFile {
my $lineNum = 0;
open(INFILE, "data/".$_[0].".xml") or die "Can't open ".$_[0].": $!";
foreach(<INFILE>) {
++$lineNum;
}
close(INFILE);
return $lineNum;
}
# Processes the file line-by-line, removing duplicate <?xml> and
# <!DOCTYPE> tags and extracting the fields listed above. It has to be
# done line-by-line (hence the use of XML::Twig rather than XML:Simple)
# rather than loading the entire .xml file into memory because the files
# are far too big to fit.
sub processFile {
my $buffer = "", my $firstItem = 1, my $currentLine = 1;
open(INFILE, "data/".$_[0].".xml") or die "Can't open ".$_[0].": $!";
unlink("details/".$_[0].".xml");
unlink("citations/".$_[0].".xml");
open(my $detailsFile, ">>details/".$_[0].".xml") or die "Can't output ".$_[0].": $!";
open(my $citationsFile, ">>citations/".$_[0].".xml") or die "Can't output ".$_[0].": $!";
# Prints the root node to the files for XML::Simple in generateSQL()
#print $detailsFile "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<PATDOC>";
#print $citationsFile "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<PATDOC>\n";
# For each line, build up a buffer (excluding the <?xml> and
# <!DOCTYPE> tags). When the next <us-patent-grant> item is reached
# (a.k.a. when the next <?xml> tag after the initial one is reached),
# run the buffer through the details and citations twigs and print
# the results to the relevant files. Then clear the buffer for the next
# <us-patent-grant>
foreach(<INFILE>) {
print "Processing line ".($currentLine++)."/".$_[1]."...\n";
#if ($_ !~ /^\<\?xml/ && $firstItem == 0) {
#if ($_ !~ /^\<\!DOCTYPE/) {
#}
#} elsif ($firstItem == 1) {
# $firstItem = 0;
#} else {
if ($_ =~ /^\<\?xml/ && $firstItem == 0) {
#print "\n----\n".$buffer."\n----\n";
$patentTwig->parse($buffer);
$patentTwig->print($detailsFile);
$citationTwig->parse($buffer);
$citationTwig->print($citationsFile);
$buffer = "";
} elsif ($_ !~ /^\<\!/ && $_ !~ /^\]\>/) {
if ($firstItem == 0) {
$string = $_;
$string =~ s/\&[a-zA-Z0-9]*;/zonk/g;
$buffer = $buffer.$string;
} else {
print $detailsFile "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<patents>";
print $citationsFile "<?xml version=\"1.0\" encoding=\"UTF-8\"?>\n<patents>\n";
$firstItem = 0;
}
}
}
print $detailsFile "</patents>";
print $citationsFile "</patents>";
close($detailsFile);
close($citationsFile);
close(INFILE);
}
# Generates an SQL dump of the database formed from analysing the .xml
# files.
sub generateSQL {
my $xml = new XML::Simple (KeyAttr=>[]);
my $details = $xml->XMLin("details/".$_[0].".xml");
unlink("sql/".$_[0].".sql");
open(my $sqlFile, ">>sql/".$_[0].".sql") or die "Can't output SQL ".$_[0].": $!";
print $sqlFile "CREATE TABLE IF NOT EXISTS `patent`\n(\n\t`pid` INT NOT NULL AUTO_INCREMENT,\n\t`pubNum` VARCHAR(32),\n\t`pubDate` DATETIME,\n\t`appNum` VARCHAR(32),\n\t`appDate` DATETIME,\n\tPRIMARY KEY(`pid`)\n);\n\nCREATE TABLE IF NOT EXISTS `patent_cite`\n(\n\t`citing_id` VARCHAR(32) NOT NULL,\n\t`cited_id` VARCHAR(32) NOT NULL,\n\tPRIMARY KEY (`citing_id`, `cited_id`)\n);\n\n";
print $sqlFile "INSERT INTO `patent` (`pubNum`, `pubDate`, `appNum`, `appDate`) VALUES";
foreach my $e (@{$details->{'PATDOC'}}) {
print $sqlFile "\n\t('".$e->{'pubnum'}."', '".$e->{'pubdate'}."', '".$e->{'appnum'}."', '".$e->{'appdate'}."'),";
}
print $sqlFile "\n\t('0', '0', '0', '0');\n\n-- This line and the above (0,0,0,0) tuple are needed due to the nature\n-- of the loop that builds the INSERT query, and the resultant SQL file\n-- being too long to edit from the end easily.\nDELETE FROM `patent` WHERE `pid` = '0';";
my $citations = $xml->XMLin("citations/".$_[0].".xml");
print $sqlFile "\n\nINSERT INTO `patent_cite` (`citing_id`, `cited_id`) VALUES";
foreach my $f (@{$citations->{'PATDOC'}}) {
my $pubNum = $f->{'pubnum'};
foreach (@{$f->{'citing'}}) {
print $sqlFile "\n\t('".$pubNum."', '".$_."'),";
}
}
print $sqlFile "\n\t('0', '0', '0', '0');\n\n-- This line and the above (0,0,0,0) tuple are needed due to the nature\n-- of the loop that builds the INSERT query, and the resultant SQL file\n-- being too long to edit from the end easily.\nDELETE FROM `patent_cite` WHERE `citing_id` = '0';";
close($sqlFile);
}

View file

@ -1,401 +0,0 @@
INSERT INTO `analysts_to_transcripts` (`analyst_id`, `transcript_id`) VALUES
(1, 0),
(2, 1),
(3, 2),
(3, 3),
(3, 4),
(3, 5),
(3, 6),
(3, 7),
(3, 8),
(3, 9),
(3, 10),
(4, 11),
(4, 12),
(4, 13),
(4, 14),
(4, 15),
(4, 16),
(4, 17),
(4, 18),
(4, 19),
(4, 20),
(4, 21),
(4, 22),
(4, 23),
(4, 24),
(4, 25),
(5, 26),
(5, 27),
(5, 28),
(6, 29),
(6, 30),
(6, 31),
(6, 32),
(6, 33),
(6, 34),
(6, 35),
(6, 36),
(6, 37),
(6, 38),
(6, 39),
(7, 40),
(7, 41),
(7, 42),
(7, 43),
(7, 44),
(7, 45),
(7, 46),
(7, 47),
(7, 48),
(8, 49),
(8, 50),
(8, 51),
(8, 52),
(8, 53),
(8, 54),
(8, 55),
(8, 56),
(8, 57),
(8, 58),
(8, 59),
(8, 60),
(8, 61),
(8, 62),
(8, 63),
(8, 64),
(8, 65),
(8, 66),
(8, 67),
(8, 68),
(9, 69),
(9, 70),
(9, 71),
(10, 72),
(10, 73),
(10, 74),
(10, 75),
(10, 76),
(10, 77),
(10, 78),
(10, 79),
(10, 80),
(10, 81),
(11, 82),
(11, 83),
(11, 84),
(11, 85),
(11, 86),
(11, 87),
(11, 88),
(11, 89),
(11, 90),
(11, 91),
(11, 92),
(11, 93),
(11, 94),
(11, 95),
(12, 96),
(12, 97),
(12, 98),
(12, 81),
(12, 99),
(13, 100),
(13, 101),
(13, 102),
(13, 103),
(13, 104),
(13, 105),
(13, 106),
(14, 107),
(14, 108),
(14, 109),
(14, 110),
(14, 111),
(14, 112),
(14, 113),
(14, 114),
(14, 115),
(14, 116),
(14, 117),
(15, 13),
(15, 118),
(15, 119),
(15, 120),
(15, 23),
(15, 121),
(16, 122),
(16, 39),
(16, 123),
(16, 124),
(16, 125),
(16, 126),
(17, 127),
(17, 128),
(17, 129),
(17, 130),
(17, 131),
(18, 132),
(18, 133),
(19, 134),
(19, 135),
(19, 136),
(19, 137),
(19, 138),
(19, 139),
(19, 140),
(19, 141),
(19, 142),
(20, 141),
(20, 143),
(20, 144),
(20, 145),
(20, 146),
(20, 142),
(20, 147),
(20, 148),
(20, 149),
(20, 95),
(20, 150),
(20, 151),
(20, 152),
(20, 153),
(21, 154),
(21, 155),
(21, 156),
(21, 157),
(21, 158),
(21, 159),
(21, 160),
(21, 161),
(21, 162),
(21, 163),
(21, 164),
(21, 165),
(21, 166),
(21, 167),
(21, 168),
(21, 169),
(21, 170),
(22, 171),
(22, 172),
(22, 173),
(22, 174),
(23, 175),
(23, 176),
(23, 177),
(23, 178),
(23, 179),
(23, 180),
(23, 181),
(24, 182),
(24, 183),
(25, 184),
(25, 185),
(25, 186),
(25, 187),
(25, 188),
(25, 189),
(25, 190),
(25, 191),
(25, 192),
(25, 193),
(25, 194),
(25, 195),
(25, 196),
(25, 197),
(25, 198),
(26, 199),
(26, 200),
(26, 201),
(26, 202),
(26, 203),
(26, 204),
(26, 205),
(26, 206),
(26, 207),
(26, 208),
(26, 209),
(26, 210),
(26, 211),
(26, 212),
(26, 213),
(27, 214),
(27, 215),
(27, 216),
(27, 44),
(27, 217),
(27, 218),
(27, 41),
(27, 219),
(27, 45),
(27, 220),
(28, 71),
(28, 70),
(30, 221),
(30, 222),
(30, 131),
(31, 223),
(31, 224),
(31, 225),
(32, 226),
(32, 85),
(32, 227),
(32, 228),
(32, 229),
(32, 230),
(32, 231),
(32, 232),
(32, 112),
(32, 233),
(32, 234),
(32, 235),
(33, 236),
(33, 237),
(33, 238),
(34, 239),
(34, 240),
(34, 241),
(34, 242),
(34, 243),
(34, 244),
(35, 245),
(35, 246),
(36, 247),
(36, 248),
(37, 249),
(37, 250),
(38, 251),
(38, 252),
(38, 253),
(39, 254),
(39, 255),
(39, 256),
(39, 257),
(39, 258),
(39, 259),
(39, 260),
(39, 261),
(39, 262),
(40, 263),
(40, 264),
(40, 265),
(41, 266),
(41, 267),
(42, 268),
(42, 269),
(42, 270),
(42, 271),
(42, 272),
(43, 190),
(43, 273),
(43, 274),
(43, 275),
(43, 276),
(43, 277),
(43, 278),
(43, 279),
(43, 280),
(43, 186),
(44, 281),
(44, 164),
(44, 282),
(44, 154),
(44, 283),
(44, 284),
(44, 285),
(44, 286),
(44, 287),
(44, 288),
(44, 289),
(44, 290),
(44, 291),
(45, 292),
(45, 293),
(45, 294),
(46, 295),
(47, 165),
(47, 296),
(47, 166),
(47, 297),
(47, 298),
(47, 299),
(47, 160),
(47, 300),
(48, 301),
(48, 302),
(48, 303),
(48, 304),
(48, 305),
(48, 306),
(48, 307),
(48, 308),
(49, 309),
(49, 310),
(49, 311),
(50, 312),
(50, 313),
(51, 314),
(52, 315),
(52, 316),
(52, 317),
(52, 318),
(53, 319),
(53, 320),
(54, 321),
(54, 322),
(54, 323),
(54, 324),
(54, 325),
(54, 326),
(54, 327),
(54, 328),
(55, 329),
(55, 330),
(55, 331),
(55, 332),
(55, 333),
(56, 334),
(56, 335),
(57, 336),
(57, 337),
(57, 338),
(57, 339),
(57, 340),
(57, 341),
(57, 342),
(57, 343),
(58, 344),
(58, 345),
(58, 238),
(58, 346),
(58, 347),
(58, 348),
(58, 349),
(58, 350),
(58, 351),
(58, 352),
(58, 353),
(58, 237),
(58, 354),
(59, 355),
(59, 356),
(59, 357),
(59, 358),
(59, 359),
(60, 360),
(60, 361),
(61, 362),
(61, 363),
(62, 364),
(62, 365);
ALTER TABLE `transcripts`
DROP COLUMN `execs`,
DROP COLUMN `analysts`;
DELETE FROM `transcripts` WHERE `id` = 1;
DELETE FROM `execs` WHERE `id` = 1;
DELETE FROM `analysts` WHERE `id` = 1;
DELETE FROM `execs_to_transcripts` WHERE `transcript_id` = 0;
DELETE FROM `analysts_to_transcripts` WHERE `transcript_id` = 0;

View file

@ -1,208 +0,0 @@
INSERT INTO `execs_to_transcripts` (`exec_id`, `transcript_id`) VALUES
(1, 0),
(2, 1),
(2, 2),
(2, 3),
(2, 4),
(3, 5),
(3, 6),
(3, 7),
(4, 8),
(4, 9),
(4, 10),
(5, 11),
(5, 12),
(5, 13),
(5, 14),
(6, 15),
(6, 16),
(6, 17),
(6, 18),
(6, 19),
(7, 20),
(7, 21),
(7, 22),
(7, 23),
(8, 24),
(8, 25),
(8, 26),
(9, 27),
(9, 28),
(9, 29),
(9, 30),
(10, 31),
(10, 32),
(11, 33),
(11, 34),
(11, 35),
(12, 36),
(12, 37),
(12, 38),
(12, 39),
(13, 40),
(13, 41),
(13, 42),
(14, 43),
(14, 44),
(14, 45),
(14, 46),
(14, 47),
(14, 48),
(14, 49),
(14, 50),
(14, 51),
(15, 52),
(15, 53),
(15, 54),
(16, 55),
(16, 56),
(16, 57),
(17, 58),
(17, 59),
(17, 60),
(17, 61),
(18, 62),
(18, 63),
(19, 64),
(19, 65),
(19, 66),
(20, 67),
(20, 68),
(21, 69),
(21, 70),
(21, 71),
(22, 72),
(22, 73),
(22, 74),
(23, 75),
(23, 76),
(23, 77),
(23, 78),
(24, 79),
(24, 80),
(24, 81),
(25, 82),
(25, 83),
(25, 84),
(26, 85),
(26, 86),
(26, 87),
(26, 88),
(27, 89),
(27, 90),
(27, 91),
(27, 92),
(27, 93),
(28, 94),
(28, 95),
(28, 96),
(29, 97),
(29, 98),
(29, 99),
(30, 100),
(30, 101),
(31, 102),
(31, 103),
(31, 104),
(31, 105),
(32, 106),
(32, 107),
(33, 108),
(33, 109),
(34, 110),
(34, 111),
(35, 112),
(35, 113),
(35, 114),
(36, 115),
(36, 116),
(36, 117),
(36, 118),
(37, 119),
(37, 120),
(37, 121),
(38, 122),
(38, 123),
(39, 124),
(39, 125),
(39, 126),
(40, 127),
(40, 128),
(40, 129),
(41, 130),
(41, 131),
(41, 132),
(41, 133),
(42, 134),
(42, 135),
(42, 136),
(42, 137),
(42, 138),
(42, 139),
(43, 140),
(43, 141),
(43, 142),
(44, 143),
(44, 144),
(44, 145),
(45, 146),
(45, 147),
(45, 148),
(46, 149),
(46, 150),
(46, 151),
(47, 152),
(47, 153),
(47, 154),
(47, 155),
(48, 156),
(48, 157),
(48, 158),
(49, 159),
(49, 160),
(49, 161),
(50, 162),
(50, 163),
(51, 164),
(51, 165),
(52, 166),
(52, 167),
(52, 168),
(53, 169),
(53, 170),
(53, 171),
(54, 172),
(54, 173),
(54, 174),
(54, 175),
(54, 176),
(54, 177),
(55, 178),
(55, 179),
(55, 180),
(56, 181),
(56, 182),
(57, 183),
(57, 184),
(57, 185),
(58, 186),
(58, 187),
(58, 188),
(58, 189),
(58, 190),
(58, 191),
(58, 192),
(58, 193),
(58, 194),
(58, 195),
(59, 196),
(59, 197),
(59, 198),
(60, 199),
(60, 200),
(60, 201),
(61, 202),
(61, 203),
(62, 204),
(62, 205),
(62, 206);

File diff suppressed because one or more lines are too long

View file

@ -1,110 +0,0 @@
-- phpMyAdmin SQL Dump
-- version 4.0.10.14
-- http://www.phpmyadmin.net
--
-- Host: localhost:3306
-- Generation Time: Dec 26, 2016 at 02:39 PM
-- Server version: 5.5.52-cll-lve
-- PHP Version: 5.6.20
SET SQL_MODE = "NO_AUTO_VALUE_ON_ZERO";
SET time_zone = "+00:00";
/*!40101 SET @OLD_CHARACTER_SET_CLIENT=@@CHARACTER_SET_CLIENT */;
/*!40101 SET @OLD_CHARACTER_SET_RESULTS=@@CHARACTER_SET_RESULTS */;
/*!40101 SET @OLD_COLLATION_CONNECTION=@@COLLATION_CONNECTION */;
/*!40101 SET NAMES utf8 */;
--
-- Database: `bengoldsworthy`
--
-- --------------------------------------------------------
--
-- Table structure for table `transcripts`
--
CREATE TABLE IF NOT EXISTS `transcripts` (
`id` int(11) NOT NULL AUTO_INCREMENT,
`title` varchar(255) DEFAULT NULL,
`company` varchar(255) DEFAULT NULL,
`execs` varchar(255) DEFAULT NULL,
`analysts` varchar(255) DEFAULT NULL,
`transcript` text,
PRIMARY KEY (`id`),
UNIQUE KEY `id` (`id`)
) ENGINE=MyISAM DEFAULT CHARSET=latin1 AUTO_INCREMENT=63 ;
--
-- Dumping data for table `transcripts`
--
INSERT INTO `transcripts` (`id`, `execs`, `analysts`) VALUES
(1, '0', '0'),
(2, '1;2;3;4', '1'),
(3, '5;6;7', '2;3;4;5;6;7;8;9;10'),
(4, '8;9;10', '11;12;13;14;15;16;17;18;19;20;21;22;23;24;25'),
(5, '11;12;13;14', '26;27;28'),
(6, '15;16;17;18;19', '29;30;31;32;33;34;35;36;37;38;39'),
(7, '20;21;22;23', '40;41;42;43;44;45;46;47;48'),
(8, '24;25;26', '49;50;51;52;53;54;55;56;57;58;59;60;61;62;63;64;65;66;67;68'),
(9, '27;28;29;30', '69;70;71'),
(10, '31;32', '72;73;74;75;76;77;78;79;80;81'),
(11, '33;34;35', '82;83;84;85;86;87;88;89;90;91;92;93;94;95'),
(12, '36;37;38;39', '96;97;98;81;99'),
(13, '40;41;42', '100;101;102;103;104;105;106'),
(14, '43;44;45;46;47;48;49;50;51', '107;108;109;110;111;112;113;114;115;116;117'),
(15, '52;53;54', '13;118;119;120;23;121'),
(16, '55;56;57', '122;39;123;124;125;126'),
(17, '58;59;60;61', '127;128;129;130;131'),
(18, '62;63', '132;133'),
(19, '64;65;66', '134;135;136;137;138;139;140;141;142'),
(20, '67;68', '141;143;144;145;146;142;147;148;149;95;150;151;152;153'),
(21, '69;70;71', '154;155;156;157;158;159;160;161;162;163;164;165;166;167;168;169;170'),
(22, '72;73;74', '171;172;173;174'),
(23, '75;76;77;78', '175;176;177;178;179;180;181'),
(24, '79;80;81', '182;183'),
(25, '82;83;84', '184;185;186;187;188;189;190;191;192;193;194;195;196;197;198'),
(26, '85;86;87;88', '199;200;201;202;203;204;205;206;207;208;209;210;211;212;213'),
(27, '89;90;91;92;93', '214;215;216;44;217;218;41;219;45;220'),
(28, '94;95;96', '71;70'),
(29, '97;98;99', ''),
(30, '100;101', '221;222;131'),
(31, '102;103;104;105', '223;224;225'),
(32, '106;107', '226;85;227;228;229;230;231;232;112;233;234;235'),
(33, '108;109', '236;237;238'),
(34, '110;111', '239;240;241;242;243;244'),
(35, '112;113;114', '245;246'),
(36, '115;116;117;118', '247;248'),
(37, '119;120;121', '249;250'),
(38, '122;123', '251;252;253'),
(39, '124;125;126', '254;255;256;257;258;259;260;261;262'),
(40, '127;128;129', '263;264;265'),
(41, '130;131;132;133', '266;267'),
(42, '134;135;136;137;138;139', '268;269;270;271;272'),
(43, '140;141;142', '190;273;274;275;276;277;278;279;280;186'),
(44, '143;144;145', '281;164;282;154;283;284;285;286;287;288;289;290;291'),
(45, '146;147;148', '292;293;294'),
(46, '149;150;151', '295'),
(47, '152;153;154;155', '165;296;166;297;298;299;160;300'),
(48, '156;157;158', '301;302;303;304;305;306;307;308'),
(49, '159;160;161', '309;310;311'),
(50, '162;163', '312;313'),
(51, '164;165', '314'),
(52, '166;167;168', '315;316;317;318'),
(53, '169;170;171', '319;320'),
(54, '172;173;174;175;176;177', '321;322;323;324;325;326;327;328'),
(55, '178;179;180', '329;330;331;332;333'),
(56, '181;182', '334;335'),
(57, '183;184;185', '336;337;338;339;340;341;342;343'),
(58, '186;187;188;189;190;191;192;193;194;195', '344;345;238;346;347;348;349;350;351;352;353;237;354'),
(59, '196;197;198', '355;356;357;358;359'),
(60, '199;200;201', '360;361'),
(61, '202;203', '362;363'),
(62, '204;205;206', '364;365');
/*!40101 SET CHARACTER_SET_CLIENT=@OLD_CHARACTER_SET_CLIENT */;
/*!40101 SET CHARACTER_SET_RESULTS=@OLD_CHARACTER_SET_RESULTS */;
/*!40101 SET COLLATION_CONNECTION=@OLD_COLLATION_CONNECTION */;